© 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. 35044
    Prev
    Next
    INDEX
    Explanations

    names and titles of people

    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
    59
    +0.06
    0.6%
    414
    +0.04
    0.5%
    269
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.06
    0.12
    48
    +0.04
    0.13
    293
    +0.04
    0.12
    Negative Logits
    olitan
    -0.38
    arella
    -0.33
     ILCS
    -0.30
    enaries
    -0.28
    hips
    -0.28
    oleon
    -0.27
    arro
    -0.27
    arios
    -0.26
    ropolis
    -0.26
    odiac
    -0.26
    POSITIVE LOGITS
    gaard
    0.39
    inges
    0.38
    backer
    0.35
    VPN
    0.34
    knife
    0.33
    runs
    0.32
    lings
    0.32
    phal
    0.32
    ble
    0.31
    lein
    0.31
    Activations Density 12.283%

    No Known Activations