© 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. 6014
    Prev
    Next
    INDEX
    Explanations

    words related to physics or chemistry concepts

    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
    253
    +0.15
    0.6%
    4
    +0.13
    0.5%
    286
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.06
    288
    +0.13
    0.06
    406
    +0.12
    0.04
    Negative Logits
    uterte
    -0.93
    omez
    -0.88
    hedral
    -0.85
    illac
    -0.82
    chnology
    -0.82
    ansom
    -0.80
    addafi
    -0.77
    alore
    -0.77
    auri
    -0.76
    robat
    -0.76
    POSITIVE LOGITS
    laus
    0.92
    ï¸
    0.90
    imir
    0.88
    ledged
    0.87
    \\\\
    0.85
    hips
    0.85
     unconditional
    0.84
    entials
    0.82
    mares
    0.81
    ãĥķ
    0.79
    Activations Density 0.726%

    No Known Activations