© 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. 2-RES-JB
    11. 9485
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or weaker emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the word "kinda" and its variations, indicating a casual or informal tone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.92
    worthiness
    -0.91
    inals
    -0.86
    iens
    -0.79
    enance
    -0.76
    ilings
    -0.75
    heid
    -0.73
    encers
    -0.73
    Journal
    -0.71
    worthy
    -0.70
    POSITIVE LOGITS
     kinda
    1.08
     darn
    0.89
     shit
    0.82
     crap
    0.79
     REALLY
    0.79
     bum
    0.78
     damn
    0.78
     fuzzy
    0.77
     silly
    0.77
     damned
    0.76
    Activations Density 0.004%

    No Known Activations