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. 0-RES-JB
    6. 8936
    Prev
    Next
    INDEX
    Explanations

    the name "Sebastian"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Sebastian" and "Bast"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IQ
    -0.86
    ollah
    -0.79
     Wizards
    -0.74
    rill
    -0.74
    Rat
    -0.73
     Rwanda
    -0.71
     Sears
    -0.71
    instein
    -0.70
     Rodham
    -0.68
     Sixers
    -0.67
    POSITIVE LOGITS
     Sebastian
    2.44
     Flor
    1.82
     Bast
    1.79
     Ana
    1.72
    Flor
    1.44
     Crist
    1.37
     Sebast
    1.37
     Frey
    1.32
     Fernando
    1.31
     Seb
    1.21
    Activations Density 0.037%

    No Known Activations