© 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 EvalsExportsinterp-engineNEWAPI 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. 8074
    Prev
    Next
    INDEX
    Explanations

    mentions of software development tools and processes

    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
    447
    +0.28
    0.9%
    6
    +0.19
    0.6%
    445
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.28
    0.02
    171
    +0.19
    0.02
    268
    +0.15
    0.02
    Negative Logits
    assic
    -1.25
    igger
    -1.21
     nomine
    -1.20
     carbohyd
    -1.19
     volunte
    -1.12
    Ħ¢
    -1.10
    staking
    -1.10
     practition
    -1.10
    parable
    -1.09
    apeshifter
    -1.09
    POSITIVE LOGITS
     Swan
    1.16
     Pes
    1.13
     NOTICE
    1.12
     Mn
    1.07
     Throughout
    1.06
     Fram
    1.05
     Walls
    1.05
     Havana
    1.02
     Yuan
    1.01
     Nag
    0.99
    Activations Density 0.216%

    No Known Activations