© 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. 22338
    Prev
    Next
    INDEX
    Explanations

    sequences with number values

    oai_token-act-pair · gpt-3.5-turbo

    spaces or sequences of whitespace characters

    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
    anyon
    -0.76
    OHN
    -0.74
     McMaster
    -0.67
    ylum
    -0.65
    ochet
    -0.62
    leground
    -0.62
    earchers
    -0.62
    gc
    -0.62
    cair
    -0.61
    alyst
    -0.61
    POSITIVE LOGITS
    3.63
     Âł
    2.56
    Âł
    2.41
     ³³
    2.14
     Âł Âł
    2.09
    ³³
    1.94
     Âł Âł Âł Âł
    1.88
    ↵Âł
    1.86
     Âł Âł Âł Âł Âł Âł Âł Âł
    1.81
    ³³³³³³³³
    1.64
    Activations Density 0.010%

    No Known Activations