© 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. 114
    Prev
    Next
    INDEX
    Explanations

    mentions of things that are perceived as interesting or impressive

    oai_token-act-pair · gpt-3.5-turbo

    expressions of positivity or enthusiasm about something being "cool."

    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
     plagued
    -0.71
     Canaver
    -0.68
     UNITED
    -0.68
     consec
    -0.64
    mediate
    -0.63
    Downloadha
    -0.61
     ravaged
    -0.61
     Fas
    -0.61
    lessly
    -0.60
     unfit
    -0.60
    POSITIVE LOGITS
    ness
    0.91
    ery
    0.89
    est
    0.82
     gadgets
    0.81
    nels
    0.81
    ¥µ
    0.80
    oola
    0.80
    lahoma
    0.80
    stuff
    0.80
     stuff
    0.78
    Activations Density 0.035%

    No Known Activations