© 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. 18716
    Prev
    Next
    INDEX
    Explanations

    mentions of professions or occupations

    oai_token-act-pair · gpt-3.5-turbo

    titles or roles of individuals in various professions

    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
    ramid
    -0.77
    fw
    -0.74
    EStreamFrame
    -0.70
     [];
    -0.66
    icum
    -0.66
    imester
    -0.66
    levant
    -0.66
    word
    -0.65
    crew
    -0.64
    amiya
    -0.64
    POSITIVE LOGITS
     extraord
    1.32
     Shaun
    1.12
     Stephen
    1.10
     Richard
    1.03
     Laura
    1.03
     Jill
    1.03
     Alan
    1.02
     Tony
    1.02
     Gina
    1.02
     David
    1.01
    Activations Density 0.283%

    No Known Activations