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. 6-RES-JB
    6. 2617
    Prev
    Next
    INDEX
    Explanations

    expressions of satisfaction or happiness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of satisfaction or positive feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 6 - joy

    No Comments

    Negative Logits
     teasp
    -0.82
     GOODMAN
    -0.78
    ourage
    -0.72
    isSpecialOrderable
    -0.72
    ujah
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.68
    hops
    -0.67
    fighter
    -0.66
    Link
    -0.66
    ghai
    -0.66
    POSITIVE LOGITS
     regards
    1.01
     impunity
    0.91
     regard
    0.90
    standing
    0.86
    awed
    0.85
     respect
    0.76
    drawn
    0.74
     what
    0.74
    animate
    0.73
    draw
    0.68
    Activations Density 0.071%

    No Known Activations