© 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 14407
    Prev
    Next
    INDEX
    Explanations

    phrases related to the explanation and exploration of cosmos and existence of life beyond Earth

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    +0.14
    0.6%
    526
    +0.12
    0.4%
    494
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.14
    0.04
    494
    +0.12
    0.04
    652
    +0.11
    0.04
    Negative Logits
    usterity
    -0.95
     Nanto
    -0.79
    fully
    -0.76
    ories
    -0.73
    Doctors
    -0.69
    iencies
    -0.69
     Stras
    -0.67
     CJ
    -0.66
    ãĥĭ
    -0.65
    cs
    -0.65
    POSITIVE LOGITS
    abouts
    1.67
    comings
    0.84
    ersed
    0.83
    fires
    0.79
    ngth
    0.79
    upon
    0.78
     illegally
    0.78
    agon
    0.76
    with
    0.75
    rn
    0.75
    Activations Density 0.510%

    No Known Activations