© 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. 2-RES-JB
    11. 2006
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to politics and law, likely focusing on individuals or entities involved in political or legal matters

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.79
    DCS
    -0.66
     Immunity
    -0.66
    ropolitan
    -0.64
    recomm
    -0.64
     Improvement
    -0.64
     Remastered
    -0.63
     Legion
    -0.61
     Volunteers
    -0.61
     Fortress
    -0.61
    POSITIVE LOGITS
     Roe
    0.98
    ppel
    0.91
    ggy
    0.86
    kus
    0.86
    pees
    0.82
    stein
    0.81
    zie
    0.76
    gger
    0.76
    hammer
    0.75
    anne
    0.75
    Activations Density 0.007%

    No Known Activations