© 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. 12882
    Prev
    Next
    INDEX
    Explanations

    organizations or groups related to fraternity or brotherhood

    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
    590
    +0.08
    0.5%
    59
    +0.07
    0.4%
    16
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.08
    0.09
    99
    +0.07
    0.05
    629
    +0.07
    0.04
    Negative Logits
    EVA
    -0.53
    atche
    -0.53
    bro
    -0.52
    prototype
    -0.52
    PRES
    -0.50
    flix
    -0.50
    reys
    -0.49
    xes
    -0.49
    plays
    -0.49
    gow
    -0.49
    POSITIVE LOGITS
     Order
    0.64
    owship
    0.61
    aternal
    0.59
    volent
    0.57
    istries
    0.55
    ocese
    0.54
    ittee
    0.53
    union
    0.52
     auxiliary
    0.52
    ctuary
    0.52
    Activations Density 0.750%

    No Known Activations