© 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. 5510
    Prev
    Next
    INDEX
    Explanations

    words related to being stuck or trapped in a situation

    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
    351
    +0.16
    0.6%
    151
    +0.14
    0.5%
    37
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.16
    0.11
    151
    +0.14
    0.11
    351
    +0.13
    0.07
    Negative Logits
    issance
    -1.00
    osterone
    -0.98
    icrobial
    -0.98
     intimid
    -0.94
    rouse
    -0.93
    agent
    -0.90
    alities
    -0.90
     suggestion
    -0.90
    edom
    -0.89
    ership
    -0.88
    POSITIVE LOGITS
     bankrupt
    1.18
    ousel
    1.09
    ©¶æ¥µ
    1.07
    ptin
    1.07
    wic
    1.03
     unprepared
    1.01
     grappling
    1.00
     reeling
    1.00
     sadd
    1.00
     dere
    0.98
    Activations Density 1.754%

    No Known Activations