© 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. 14766
    Prev
    Next
    INDEX
    Explanations

    entities that are the top or leading in some aspect or category

    oai_token-act-pair · gpt-3.5-turbo

    terms related to roles, positions, or significant participants in various contexts

    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
    fw
    -0.65
    ancies
    -0.65
     inner
    -0.63
     gust
    -0.63
    tnc
    -0.62
    itional
    -0.59
    cgi
    -0.59
    kay
    -0.58
    ucks
    -0.58
    jud
    -0.58
    POSITIVE LOGITS
    REDACTED
    0.82
     (>
    0.74
    代
    0.73
     imaginable
    0.70
     EVER
    0.66
    UGC
    0.66
    Reviewer
    0.65
    ãĤ¬
    0.65
     thereof
    0.65
     toget
    0.65
    Activations Density 0.265%

    No Known Activations