© 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. 4-RES-JB
    11. 10216
    Prev
    Next
    INDEX
    Explanations

    organizations or entities that are related to specific industries or fields, such as sports leagues or associations

    oai_token-act-pair · gpt-3.5-turbo

    references to national organizations and associations

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

    No Comments

    Negative Logits
     sidx
    -0.75
    idious
    -0.75
    bye
    -0.73
    between
    -0.64
     fins
    -0.64
     mids
    -0.64
     Canaver
    -0.64
    called
    -0.63
    orious
    -0.61
    depth
    -0.60
    POSITIVE LOGITS
    QL
    0.82
    ictionary
    0.77
    oppable
    0.72
    ufact
    0.68
    ensical
    0.66
    owment
    0.66
    akable
    0.64
    SPA
    0.64
    ailability
    0.63
    ographics
    0.63
    Activations Density 0.120%

    No Known Activations