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. 2-RES-JB
    6. 19987
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Chapman."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly "Chapman."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ration
    -0.73
    arching
    -0.71
    journal
    -0.69
    fitting
    -0.69
    LEASE
    -0.67
    PUT
    -0.67
    egal
    -0.66
    pg
    -0.66
    berman
    -0.65
    vern
    -0.64
    POSITIVE LOGITS
     Chapman
    1.25
    halla
    0.86
     Henderson
    0.79
    ause
    0.79
     DeV
    0.75
     Chandler
    0.74
    otte
    0.74
     Hots
    0.74
    ville
    0.72
     Hughes
    0.71
    Activations Density 0.012%

    No Known Activations