© 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. 14094
    Prev
    Next
    INDEX
    Explanations

    actions involving movement and direction, particularly the direction of passing a ball

    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
    765
    +0.10
    0.5%
    240
    +0.10
    0.4%
    194
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.10
    0.27
    435
    +0.10
    0.05
    765
    +0.10
    0.11
    Negative Logits
    atically
    -0.84
    assadors
    -0.79
    etimes
    -0.79
    REC
    -0.78
    anned
    -0.77
    aton
    -0.77
    ifi
    -0.76
     mathemat
    -0.74
    atis
    -0.74
    usters
    -0.74
    POSITIVE LOGITS
     shoulder
    1.09
     hand
    1.07
     wing
    1.06
     flank
    1.05
     thigh
    1.00
     forearm
    0.96
     side
    0.95
     leg
    0.93
     thumb
    0.92
     foot
    0.88
    Activations Density 12.541%

    No Known Activations