© 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. 0-RES-JB
    11. 1189
    Prev
    Next
    INDEX
    Explanations

    symbols and characters that are part of an encoded language or code

    oai_token-act-pair · gpt-3.5-turbo

    unique characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brand
    -0.76
     Quad
    -0.73
     dyn
    -0.73
     Carbon
    -0.70
     Carth
    -0.69
     Chal
    -0.68
     Martin
    -0.67
     Cars
    -0.66
    cius
    -0.66
    las
    -0.65
    POSITIVE LOGITS
    ãģ
    3.71
    ãģĨ
    3.29
    ãģĹ
    3.21
    ãģĦ
    3.08
    ãģı
    2.93
    ãģį
    2.79
    ãģĻ
    2.74
    ãģ£
    2.65
    ãĤĬ
    2.59
    ãĤ
    2.59
    Activations Density 0.014%

    No Known Activations