© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1634
    Prev
    Next
    INDEX
    Explanations

    phrases related to social, scientific, or organizational contexts

    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
    247
    +0.22
    0.7%
    171
    +0.18
    0.6%
    292
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.22
    0.08
    288
    +0.18
    0.12
    575
    +0.15
    0.11
    Negative Logits
     rib
    -1.07
    rosso
    -1.00
    heed
    -0.97
    iolet
    -0.94
     wat
    -0.94
    alone
    -0.91
    oggles
    -0.89
     Maple
    -0.87
    orsi
    -0.87
    umbo
    -0.86
    POSITIVE LOGITS
    forts
    1.14
    waters
    1.13
    verse
    1.12
    liest
    1.10
    rar
    1.04
     of
    0.98
    posts
    0.97
    pires
    0.96
    ivation
    0.96
     thereof
    0.96
    Activations Density 1.924%

    No Known Activations