© 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. 16371
    Prev
    Next
    INDEX
    Explanations

    words related to fractals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fractals and fractal geometry

    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
     Bradley
    -0.69
    still
    -0.67
    toe
    -0.65
    ibaba
    -0.65
    wine
    -0.64
     Ambrose
    -0.64
    laughs
    -0.63
    tainment
    -0.60
     WWE
    -0.60
     Herrera
    -0.60
    POSITIVE LOGITS
     fract
    1.39
     mathemat
    1.01
    umpy
    0.96
    raph
    0.87
    ĩ
    0.81
     newsp
    0.79
    etsk
    0.78
    ilateral
    0.77
    ĸļ
    0.76
    rir
    0.76
    Activations Density 0.024%

    No Known Activations