© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 31409
    Prev
    Next
    INDEX
    Explanations

    controls and mechanisms used to operate devices, ranging from brain-sensing headbands to gaming controls to remote control drones

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.18
    1.0%
    218
    +0.11
    0.6%
    540
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.18
    0.10
    578
    +0.11
    0.04
    97
    +0.10
    0.04
    Negative Logits
    iversary
    -0.83
    olit
    -0.74
    iatus
    -0.65
    olid
    -0.62
    tein
    -0.61
     Gleaming
    -0.60
    uary
    -0.60
    entimes
    -0.60
    ãĤ§
    -0.60
    osate
    -0.58
    POSITIVE LOGITS
     levers
    0.83
     steering
    0.74
     commands
    0.72
    eer
    0.71
    eering
    0.70
    eers
    0.70
     inputs
    0.70
     cursor
    0.68
     Commands
    0.68
     knob
    0.68
    Activations Density 10.155%

    No Known Activations