© 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. 3-RES-JB
    11. 7025
    Prev
    Next
    INDEX
    Explanations

    words related to theaters or performance venues

    oai_token-act-pair · gpt-3.5-turbo

    references to specific venues and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     penetrating
    -0.69
    lished
    -0.68
     Leilan
    -0.62
     Benz
    -0.61
    enegger
    -0.61
     informants
    -0.60
     Alph
    -0.58
     Squirrel
    -0.58
     Devils
    -0.57
     Christensen
    -0.57
    POSITIVE LOGITS
    ithe
    1.45
    atre
    1.43
    rette
    0.96
    cium
    0.90
    aque
    0.90
    selage
    0.90
    ocity
    0.89
    aviour
    0.86
    ater
    0.84
    aukee
    0.82
    Activations Density 0.007%

    No Known Activations