© 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. 9550
    Prev
    Next
    INDEX
    Explanations

    words containing the character "è"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "è" in the text

    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
    frames
    -0.73
    assic
    -0.68
    multipl
    -0.67
    frame
    -0.67
    ording
    -0.66
    utterstock
    -0.63
    lift
    -0.59
    butt
    -0.59
    EStreamFrame
    -0.58
    ritic
    -0.58
    POSITIVE LOGITS
    è
    1.30
    vre
    0.98
     é
    0.94
    ¬
    0.88
    lette
    0.86
     dé
    0.85
    ¯¯¯¯
    0.84
     Ãł
    0.81
     ré
    0.79
     Ré
    0.79
    Activations Density 0.004%

    No Known Activations