© 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. 22658
    Prev
    Next
    INDEX
    Explanations

    phrases relating to physical attributes or characteristics followed by opinions or judgments

    oai_token-act-pair · gpt-3.5-turbo

    references to physical appearances and societal expectations related to attractiveness

    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
    erenn
    -0.69
    nsic
    -0.67
    versible
    -0.61
    quartered
    -0.61
    gradation
    -0.59
    atility
    -0.59
    innacle
    -0.58
    udos
    -0.58
    inently
    -0.57
     cumulative
    -0.56
    POSITIVE LOGITS
     haha
    1.30
     lol
    1.18
     ;)
    1.18
     anymore
    1.17
     :(
    1.07
    !.
    1.04
    ?).
    1.03
     :)
    1.01
     :-)
    0.99
     ðŁĻĤ
    0.98
    Activations Density 1.043%

    No Known Activations