© 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. 13616
    Prev
    Next
    INDEX
    Explanations

    people's names, potentially related to political or newsworthy individuals

    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
    526
    +0.20
    0.7%
    23
    +0.17
    0.6%
    62
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.20
    0.06
    326
    +0.17
    0.06
    659
    +0.16
    0.05
    Negative Logits
    OUNT
    -1.02
     Kod
    -0.97
    IFIED
    -0.91
    etheless
    -0.91
     eleph
    -0.91
    sembly
    -0.91
    foundation
    -0.89
    phis
    -0.89
    doms
    -0.85
    å¹
    -0.85
    POSITIVE LOGITS
    chnology
    1.46
    pping
    1.26
    ste
    1.25
    uben
    1.25
    lla
    1.20
    rer
    1.19
    rers
    1.19
    ved
    1.17
    achy
    1.17
    aling
    1.16
    Activations Density 1.119%

    No Known Activations