© 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. 9011
    Prev
    Next
    INDEX
    Explanations

    phrases related to recognizing excellence or high quality

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating high quality or excellence

    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
    inez
    -0.73
    empt
    -0.73
    ogenesis
    -0.71
    ipation
    -0.71
     fetus
    -0.66
    angered
    -0.64
    cessive
    -0.64
     containment
    -0.64
    bian
    -0.63
    initial
    -0.63
    POSITIVE LOGITS
     reputable
    1.28
     talented
    1.13
     respected
    1.04
     renowned
    1.00
     businessmen
    1.00
     professors
    0.99
     esteemed
    0.99
     eminent
    0.98
     knowledgeable
    0.98
     fellows
    0.97
    Activations Density 1.003%

    No Known Activations