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. 13793
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'excess' or variations of it within the text

    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
    +0.20
    0.7%
    375
    +0.16
    0.6%
    271
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.10
    271
    +0.16
    0.04
    647
    +0.15
    0.05
    Negative Logits
    Äĩ
    -0.93
    HCR
    -0.87
    udder
    -0.82
    andum
    -0.82
    ongyang
    -0.80
    ching
    -0.80
    byn
    -0.79
     Brist
    -0.79
    ect
    -0.79
    chens
    -0.78
    POSITIVE LOGITS
    es
    1.27
    ively
    1.05
    entimes
    0.99
     capacity
    0.97
     baggage
    0.93
    itures
    0.93
    ebin
    0.91
    ibilities
    0.90
     quantities
    0.88
    eatures
    0.85
    Activations Density 1.109%

    No Known Activations