© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 39652
    Prev
    Next
    INDEX
    Explanations

    phrases related to directions and locations

    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
    393
    +0.15
    0.6%
    92
    +0.11
    0.5%
    560
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.12
    608
    +0.11
    0.16
    385
    +0.11
    0.14
    Negative Logits
     wont
    -0.67
     TAMADRA
    -0.65
     Takes
    -0.63
     aborted
    -0.62
    packages
    -0.61
     Catalyst
    -0.61
    ï
    -0.60
    ahead
    -0.60
     Printed
    -0.59
    leground
    -0.58
    POSITIVE LOGITS
     extent
    1.43
    venge
    1.35
    rouse
    1.20
     detriment
    1.16
    merce
    0.98
     tune
    0.89
    ffer
    0.83
    oint
    0.82
     degree
    0.81
    ue
    0.81
    Activations Density 9.464%

    No Known Activations