© 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. 1-RES-JB
    11. 5494
    Prev
    Next
    INDEX
    Explanations

    words related to extreme or strong emotions, judgments, or characterizations

    oai_token-act-pair · gpt-3.5-turbo

    the word "utterly" and its variations, indicating a strong emphasis or absolute nature in descriptions or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioch
    -0.81
    enegger
    -0.79
    anwhile
    -0.78
    arters
    -0.78
    icipated
    -0.78
     Occupations
    -0.77
     Agents
    -0.72
    anners
    -0.71
    hops
    -0.71
    hao
    -0.70
    POSITIVE LOGITS
    ulously
    0.83
     baffled
    0.80
     annihil
    0.78
     bewild
    0.76
    BuyableInstoreAndOnline
    0.75
    otally
    0.74
     satisfied
    0.74
     irre
    0.73
     delighted
    0.72
     behold
    0.71
    Activations Density 0.009%

    No Known Activations