Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23313
    Prev
    Next
    INDEX
    Explanations

    dates and times

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and events related to announcements or releases

    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
     grooming
    -0.54
     perceived
    -0.53
     tended
    -0.51
     psychologically
    -0.51
     sweeping
    -0.51
     supposed
    -0.50
     traced
    -0.50
     pushed
    -0.50
     fundamentally
    -0.49
     apprehended
    -0.48
    POSITIVE LOGITS
    sic
    0.78
     :)
    0.75
     ;)
    0.75
     (@
    0.73
    Ô
    0.71
     ðŁĻĤ
    0.68
    .).
    0.67
     :-)
    0.67
    .]
    0.66
    nesday
    0.65
    Activations Density 1.582%

    No Known Activations