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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 15618
    Prev
    Next
    INDEX
    Explanations

    instances of rarity or uncommonness

    oai_token-act-pair · gpt-3.5-turbo

    references to rarity or uncommonness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mosp
    -0.77
    verning
    -0.72
    atche
    -0.71
    akespeare
    -0.68
    atever
    -0.66
    itution
    -0.65
    ipation
    -0.64
     Andrews
    -0.63
    atchewan
    -0.63
     padd
    -0.62
    POSITIVE LOGITS
     occurrence
    0.99
    istically
    0.93
     occurrences
    0.88
    spect
    0.82
    ties
    0.80
    ty
    0.79
     exceptions
    0.77
    bs
    0.77
    entimes
    0.75
    fy
    0.75
    Activations Density 0.031%

    No Known Activations