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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 8471
    Prev
    Next
    INDEX
    Explanations

    phrases related to NFL football coach Jim Caldwell

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the names "Caldwell" and "Kidd"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psons
    -0.84
    amins
    -0.78
    ylum
    -0.74
    lier
    -0.71
     pancakes
    -0.70
    ishers
    -0.70
    hm
    -0.69
    inity
    -0.69
     Refugees
    -0.64
    isher
    -0.64
    POSITIVE LOGITS
     Caldwell
    1.04
     Gillespie
    0.73
    yrinth
    0.71
    icago
    0.70
    orah
    0.68
    erous
    0.68
    hare
    0.66
    ithing
    0.66
     subdivision
    0.65
    ateral
    0.64
    Activations Density 0.022%

    No Known Activations