© 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. 9544
    Prev
    Next
    INDEX
    Explanations

    adjectives describing extraordinary or exceptional experiences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "incredible" and its variations to express strong positive sentiment

    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
    pai
    -0.87
    avis
    -0.82
    vere
    -0.76
    PD
    -0.73
    nan
    -0.70
    abet
    -0.68
    ©¶æ
    -0.68
    geist
    -0.67
    getting
    -0.66
    deen
    -0.66
    POSITIVE LOGITS
     incredible
    0.98
     amazing
    0.85
     amounts
    0.85
     unbeliev
    0.83
    NESS
    0.82
     amount
    0.80
     lengths
    0.79
     feat
    0.79
     feats
    0.79
     earthqu
    0.78
    Activations Density 0.017%

    No Known Activations