© 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. 0-RES-JB
    11. 1307
    Prev
    Next
    INDEX
    Explanations

    locations or addresses

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms related to geographical locations or sites

    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
     mockery
    -0.75
     applause
    -0.71
     criticism
    -0.71
     expectations
    -0.68
     scorn
    -0.68
    empt
    -0.64
     debates
    -0.63
     ridicule
    -0.63
     whirlwind
    -0.63
    laughter
    -0.62
    POSITIVE LOGITS
     located
    3.52
     situated
    2.48
     Located
    2.47
    Located
    2.01
     headquartered
    1.70
     locate
    1.62
     housed
    1.49
     stationed
    1.48
     locating
    1.41
     residing
    1.39
    Activations Density 0.022%

    No Known Activations