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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 14141
    Prev
    Next
    INDEX
    Explanations

    text related to dissenting opinions or actions, particularly in the context of legal or governmental matters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    +0.15
    0.7%
    19
    +0.13
    0.5%
    616
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.17
    722
    +0.13
    0.07
    389
    +0.12
    0.07
    Negative Logits
     Archdemon
    -0.77
     Werewolf
    -0.75
    çĦ
    -0.74
     stakes
    -0.72
    FORE
    -0.72
     Gat
    -0.70
     Goff
    -0.69
    WAYS
    -0.69
     Elves
    -0.68
    glers
    -0.67
    POSITIVE LOGITS
    ipation
    1.39
    ociation
    1.39
    imilar
    1.38
    oci
    1.35
    ident
    1.33
    ociated
    1.29
    ension
    1.27
    olving
    1.27
    ertation
    1.18
    ociate
    1.14
    Activations Density 6.113%

    No Known Activations