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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7856
    Prev
    Next
    INDEX
    Explanations

    positive expressions of pride

    oai_token-act-pair · gpt-3.5-turbo

    expressions of pride or admiration

    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
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.97
    interrupted
    -0.69
    vice
    -0.69
    ondo
    -0.67
    oller
    -0.66
    uto
    -0.65
     downward
    -0.65
    ockets
    -0.64
    scan
    -0.63
    ettlement
    -0.63
    POSITIVE LOGITS
     accomplishment
    0.94
     accomplishments
    0.88
     achievement
    0.77
     achievements
    0.74
     Commit
    0.71
    ¥
    0.71
     honour
    0.69
    ¥µ
    0.67
     integrity
    0.67
     victory
    0.67
    Activations Density 0.096%

    No Known Activations