© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 2692
    Prev
    Next
    INDEX
    Explanations

    references to the location "Madison Square."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations, particularly squares

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hetical
    -0.73
    oad
    -0.72
    nell
    -0.71
    ufact
    -0.70
    hesis
    -0.69
    opathy
    -0.68
    omer
    -0.68
    ERAL
    -0.68
    orship
    -0.67
    ulas
    -0.66
    POSITIVE LOGITS
     Enix
    1.35
     Mile
    0.88
     plaza
    0.84
    pants
    0.82
     Garden
    0.72
     Ventures
    0.69
    cars
    0.66
    assi
    0.65
    Walk
    0.65
    Aren
    0.65
    Activations Density 0.021%

    No Known Activations