© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 32521
    Prev
    Next
    INDEX
    Explanations

    words related to physical activities, exercise, and athleticism

    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
    485
    +0.02
    0.4%
    195
    +0.02
    0.4%
    270
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.02
    0.10
    356
    +0.02
    -0.01
    485
    +0.02
    0.12
    Negative Logits
     Heads
    -0.14
     Bots
    -0.14
    kefeller
    -0.14
     patched
    -0.14
    å§«
    -0.14
     Syndicate
    -0.13
    uploads
    -0.13
     Pact
    -0.13
     mosaic
    -0.13
     lump
    -0.13
    POSITIVE LOGITS
    lete
    0.19
    letes
    0.17
    VERTISEMENT
    0.17
    olesterol
    0.16
    onomic
    0.16
    metics
    0.16
    ã
    0.15
    itness
    0.15
    icion
    0.15
    odynamic
    0.15
    Activations Density 19.065%

    No Known Activations