© 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. 14720
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals, potentially from different contexts

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly of individuals and institutions

    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
    axy
    -0.68
    fix
    -0.66
    FORE
    -0.65
    fixes
    -0.63
    bsite
    -0.63
    ths
    -0.62
     crawl
    -0.60
    hist
    -0.60
     hips
    -0.59
    ighter
    -0.59
    POSITIVE LOGITS
     Sturgeon
    0.84
    nikov
    0.82
    stown
    0.74
    elson
    0.74
    redits
    0.73
    osaurs
    0.72
     Davidson
    0.72
    irtual
    0.71
    CTV
    0.71
    hyde
    0.67
    Activations Density 0.020%

    No Known Activations