© 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. 5537
    Prev
    Next
    INDEX
    Explanations

    phrases related to achieving success or winning, specifically emphasizing triumph and accomplishment

    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
    288
    +0.31
    1.1%
    444
    +0.17
    0.6%
    183
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.31
    0.09
    444
    +0.17
    0.06
    335
    +0.16
    0.06
    Negative Logits
     notor
    -0.91
     pores
    -0.87
    ipedia
    -0.86
    ridges
    -0.86
     quir
    -0.86
    esthetic
    -0.86
    redit
    -0.84
    pper
    -0.82
    uci
    -0.81
    oen
    -0.80
    POSITIVE LOGITS
    antly
    1.20
    Sham
    1.03
    enance
    0.99
    stroke
    0.94
    hower
    0.94
    achi
    0.93
    bringer
    0.92
    alist
    0.90
     defeat
    0.89
    cry
    0.88
    Activations Density 1.125%

    No Known Activations