© 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. 9970
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names of entities

    oai_token-act-pair · gpt-3.5-turbo

    specific named entities or proper nouns

    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
    ĸļ
    -0.93
    enegger
    -0.81
    rawdownloadcloneembedreportprint
    -0.77
    hement
    -0.72
    anguage
    -0.71
    emonium
    -0.67
     Panzer
    -0.67
    itent
    -0.66
    mble
    -0.66
    eers
    -0.65
    POSITIVE LOGITS
    ½
    0.80
    Share
    0.69
    ·
    0.69
    ¶
    0.69
    «
    0.69
    ¿
    0.68
    ³
    0.67
    Ĵ
    0.66
    µ
    0.66
    ģ
    0.65
    Activations Density 0.377%

    No Known Activations