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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10997
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of people and businesses

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals, particularly those with the last name 'Neill' and 'Gillespie'

    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
    Ranked
    -0.73
    cgi
    -0.71
    thumbnails
    -0.69
    nces
    -0.68
    role
    -0.66
    stroke
    -0.66
    amaz
    -0.65
    VALUE
    -0.64
    mate
    -0.64
    lif
    -0.64
    POSITIVE LOGITS
     Enterprises
    0.88
    Neill
    0.83
    acht
    0.80
    igon
    0.78
    cott
    0.78
     Manor
    0.75
    ZI
    0.74
    cliffe
    0.74
    umann
    0.73
     Gould
    0.73
    Activations Density 0.014%

    No Known Activations