© 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. 6676
    Prev
    Next
    INDEX
    Explanations

    references to specific days of celebrations or events

    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
    699
    +0.03
    0.5%
    743
    +0.03
    0.4%
    302
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    110
    +0.03
    0.01
    708
    +0.03
    0.01
    727
    +0.03
    0.01
    Negative Logits
    Clar
    -0.22
    icates
    -0.20
    icate
    -0.20
    ocket
    -0.20
    icult
    -0.20
    iqu
    -0.19
    icating
    -0.19
    ils
    -0.19
    etting
    -0.18
    ighting
    -0.18
    POSITIVE LOGITS
    ternity
    0.20
    enko
    0.18
    akeru
    0.18
    emale
    0.17
    beard
    0.17
    backer
    0.17
     Birthday
    0.17
     Simulation
    0.17
     Commando
    0.17
    elsius
    0.17
    Activations Density 0.051%

    No Known Activations