© 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. 11-RES-JB
    11. 4208
    Prev
    Next
    INDEX
    Explanations

    keywords related to technical information such as captions, page numbers, and formatting symbols

    oai_token-act-pair · gpt-3.5-turbo

    tokens related to captions or labels in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     112
    -0.77
     224
    -0.76
     82
    -0.72
     Crawford
    -0.69
     138
    -0.68
     78
    -0.67
     millisec
    -0.65
     exchanges
    -0.65
     1932
    -0.64
     84
    -0.64
    POSITIVE LOGITS
    5
    1.23
     5
    1.05
    five
    0.84
    ķ
    0.84
    ahar
    0.82
    525
    0.80
     525
    0.78
    505
    0.76
    ĸļ
    0.74
    fifth
    0.74
    Activations Density 0.070%

    No Known Activations