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. 9-RES-JB
    6. 22296
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their associated titles or positions

    oai_token-act-pair · gpt-3.5-turbo

    names and titles associated with people in various professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geries
    -0.80
    aceae
    -0.77
     scraps
    -0.74
    othal
    -0.71
    itized
    -0.71
     overhe
    -0.71
    ocry
    -0.70
    rums
    -0.69
    isphere
    -0.69
    rarily
    -0.69
    POSITIVE LOGITS
     Director
    1.54
    Director
    1.49
     Chair
    1.45
     Founder
    1.45
     Managing
    1.42
     Coordinator
    1.41
     CEO
    1.38
     Associate
    1.36
     director
    1.34
    CEO
    1.32
    Activations Density 0.685%

    No Known Activations