© 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. 6-RES-JB
    11. 1673
    Prev
    Next
    INDEX
    Explanations

    sections mentioning various news sources and reporters

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     charm
    -0.69
    rox
    -0.62
     rog
    -0.61
     Ally
    -0.58
    ounds
    -0.58
    hement
    -0.58
    agnetic
    -0.56
    uca
    -0.56
     precaution
    -0.55
    properties
    -0.55
    POSITIVE LOGITS
    ³³³³³³³³
    0.83
    rawdownloadcloneembedreportprint
    0.78
    ³³³
    0.77
    ³³³³³³³³³³³³³³³³
    0.76
     à¨
    0.70
     TED
    0.69
    BBC
    0.68
    NAS
    0.68
     Âł Âł
    0.68
    Bir
    0.68
    Activations Density 0.207%

    No Known Activations