© 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. 13310
    Prev
    Next
    INDEX
    Explanations

    dates and locations in historical events

    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
    88
    +0.12
    0.5%
    283
    +0.12
    0.4%
    544
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    544
    +0.12
    0.07
    70
    +0.12
    0.07
    483
    +0.12
    0.06
    Negative Logits
    ament
    -0.83
     Trap
    -0.81
    utenberg
    -0.80
    atile
    -0.79
    ulators
    -0.78
    atures
    -0.78
    alities
    -0.77
    cern
    -0.76
    iets
    -0.76
    resa
    -0.75
    POSITIVE LOGITS
    £ı
    1.02
    las
    0.96
    soever
    0.91
    rh
    0.86
    ij士
    0.82
     cents
    0.82
     sir
    0.82
    lege
    0.81
    loo
    0.80
    Salt
    0.78
    Activations Density 0.730%

    No Known Activations