© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6647
    Prev
    Next
    INDEX
    Explanations

    mentions related to software version numbers or technical specifications

    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
    476
    +0.05
    0.5%
    504
    +0.05
    0.5%
    409
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.05
    0.03
    373
    +0.05
    -0.01
    406
    +0.05
    0.02
    Negative Logits
    ãĥĵ
    -0.34
    akuya
    -0.33
    ãĤ«
    -0.32
     Marketable
    -0.32
    ãĥĩãĤ£
    -0.30
    ãĥĥãĥĪ
    -0.30
    ndra
    -0.29
     Votes
    -0.29
     Karma
    -0.29
     Protoss
    -0.28
    POSITIVE LOGITS
    align
    0.36
    ascript
    0.35
    ocument
    0.34
    area
    0.34
    opot
    0.34
    doi
    0.33
    iliary
    0.33
    endar
    0.33
    eteen
    0.32
    amera
    0.31
    Activations Density 0.069%

    No Known Activations