© 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. 12932
    Prev
    Next
    INDEX
    Explanations

    verbs related to ensuring the proper treatment or handling of situations

    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
    307
    +0.17
    0.5%
    0
    +0.17
    0.5%
    762
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.17
    0.11
    307
    +0.17
    0.09
    762
    +0.15
    0.10
    Negative Logits
    orno
    -1.13
    iens
    -1.05
    raltar
    -1.03
    ists
    -1.02
    ista
    -0.98
     subscriptions
    -0.96
     impossibility
    -0.96
    orem
    -0.96
    ocene
    -0.95
    azi
    -0.95
    POSITIVE LOGITS
     behaved
    1.54
     suited
    1.35
     formatted
    1.30
     clothed
    1.29
    educated
    1.28
    buff
    1.25
    ãĤ©
    1.25
     educated
    1.24
     disguised
    1.22
     understood
    1.21
    Activations Density 0.908%

    No Known Activations