© 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. 1793
    Prev
    Next
    INDEX
    Explanations

    first-person quotes

    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
    393
    +0.19
    0.6%
    430
    +0.19
    0.6%
    255
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.19
    0.10
    255
    +0.19
    0.08
    729
    +0.15
    0.07
    Negative Logits
    anmar
    -1.11
    »Ĵ
    -1.01
    ·
    -0.99
    oph
    -0.97
    etheless
    -0.97
    ²¾
    -0.96
    anuts
    -0.95
    eb
    -0.95
    ijing
    -0.94
    ingu
    -0.93
    POSITIVE LOGITS
     reads
    1.58
    said
    1.43
     says
    1.36
     said
    1.30
     recalls
    1.27
     wrote
    1.19
     recalled
    1.17
     writes
    1.16
     joked
    1.14
     remarked
    1.13
    Activations Density 1.562%

    No Known Activations