© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 14175
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations, specifically focusing on the state of North Carolina

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Carolina" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Picture
    -0.83
    Lens
    -0.83
    algia
    -0.82
    gerald
    -0.82
    loo
    -0.79
    uably
    -0.78
    matically
    -0.78
    cause
    -0.77
    rahim
    -0.75
    lords
    -0.73
    POSITIVE LOGITS
     Hurricanes
    1.24
     Carolina
    1.15
    olina
    1.04
     Wilmington
    1.03
     Panthers
    1.03
     Asheville
    0.95
     Courage
    0.93
     Raleigh
    0.91
    boro
    0.85
     Hornets
    0.84
    Activations Density 0.041%

    No Known Activations