© 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. 2713
    Prev
    Next
    INDEX
    Explanations

    names of journalists and media personalities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of people

    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
    fecture
    -0.84
     lockout
    -0.73
    worldly
    -0.72
    cipline
    -0.70
    ahime
    -0.67
     dracon
    -0.66
    agara
    -0.64
     haunted
    -0.64
    raints
    -0.63
    âĶĢâĶĢ
    -0.62
    POSITIVE LOGITS
     Shapiro
    1.04
     Bernstein
    1.02
     Greenwald
    0.99
     McInt
    0.98
     McCl
    0.90
     Friedman
    0.88
     Krugman
    0.87
     Schiff
    0.87
     Levin
    0.87
     Hannity
    0.86
    Activations Density 0.290%

    No Known Activations