Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 461
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty about future outcomes

    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
    158
    +0.11
    0.5%
    99
    +0.11
    0.5%
    579
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    579
    +0.11
    0.07
    718
    +0.11
    0.08
    762
    +0.11
    0.08
    Negative Logits
    raint
    -0.81
    emia
    -0.78
    imilar
    -0.78
    illin
    -0.76
    illary
    -0.76
    Kin
    -0.75
    cius
    -0.75
    urat
    -0.75
    hib
    -0.74
    ounding
    -0.74
    POSITIVE LOGITS
    theless
    1.12
     dreamed
    1.00
     EVER
    0.94
     existed
    0.89
     doubted
    0.88
     married
    0.83
     achieve
    0.83
     stray
    0.82
     reconcil
    0.80
     attain
    0.80
    Activations Density 0.872%

    No Known Activations