© 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. 14245
    Prev
    Next
    INDEX
    Explanations

    sequences of letters and numbers that don't form recognizable words or phrases

    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
    289
    +0.10
    0.5%
    167
    +0.10
    0.4%
    742
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.02
    392
    +0.10
    0.02
    639
    +0.10
    0.01
    Negative Logits
    Bra
    -0.73
    birds
    -0.71
     amen
    -0.70
    thal
    -0.70
    uca
    -0.67
    hazard
    -0.66
    bole
    -0.66
    forth
    -0.66
     Bris
    -0.66
    currency
    -0.65
    POSITIVE LOGITS
    ruct
    0.97
    ocument
    0.79
    escription
    0.77
    itions
    0.74
    nect
    0.72
    uthor
    0.72
    agram
    0.71
    }}}
    0.71
    itionally
    0.71
    ouble
    0.71
    Activations Density 0.098%

    No Known Activations