© 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. 788
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to the theme of community

    oai_token-act-pair · gpt-3.5-turbo

    references to various global and national entities

    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
     sqor
    -0.76
    borgh
    -0.71
    bourg
    -0.70
    SpaceEngineers
    -0.67
     [+
    -0.66
    Sem
    -0.65
    soever
    -0.63
     possession
    -0.61
    Footnote
    -0.61
     Sell
    -0.61
    POSITIVE LOGITS
     tremb
    0.97
     revolves
    0.94
     erupted
    0.88
     itself
    0.87
     reacts
    0.85
    wide
    0.85
     reacted
    0.84
     suffers
    0.82
     thri
    0.81
     evolves
    0.81
    Activations Density 0.319%

    No Known Activations