© 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. 45442
    Prev
    Next
    INDEX
    Explanations

    technical details and commands related to computer systems

    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
    640
    +0.16
    0.7%
    393
    +0.13
    0.6%
    385
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.16
    0.18
    393
    +0.13
    0.18
    385
    +0.12
    0.12
    Negative Logits
    izabeth
    -0.80
    oras
    -0.76
    avorite
    -0.74
    yne
    -0.73
    ynes
    -0.72
     Pengu
    -0.72
    orie
    -0.72
    thood
    -0.70
    anamo
    -0.69
    urized
    -0.69
    POSITIVE LOGITS
     Logged
    0.88
    ERROR
    0.87
     Invalid
    0.87
     Detected
    0.85
     Unknown
    0.80
     Test
    0.76
    library
    0.75
    Pers
    0.75
    amd
    0.75
     undefined
    0.73
    Activations Density 5.714%

    No Known Activations