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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14141
    Prev
    Next
    INDEX
    Explanations

    mentions of dissent, dissenters, dissolving, dissidents, and dissociation

    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
    195
    +0.19
    0.6%
    288
    +0.18
    0.6%
    526
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.11
    195
    +0.18
    0.02
    658
    +0.14
    0.04
    Negative Logits
    çĦ
    -1.01
     stakes
    -0.94
    ttes
    -0.90
     Archdemon
    -0.90
     Sochi
    -0.88
     Werewolf
    -0.87
     Ducks
    -0.87
    WAYS
    -0.87
     Mara
    -0.87
     Gat
    -0.86
    POSITIVE LOGITS
    ipation
    1.65
    ociation
    1.53
    imilar
    1.48
    ociated
    1.44
    ension
    1.44
    ident
    1.44
    olving
    1.39
    ertation
    1.37
    oci
    1.36
    ociate
    1.32
    Activations Density 1.223%

    No Known Activations