© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9117
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to permissions or requests to reproduce content

    oai_token-act-pair · gpt-3.5-turbo

    references to permissions related to reprinting or publishing content

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

    No Comments

    Negative Logits
    ¯¯¯¯
    -0.80
    omen
    -0.75
    Ĭ±
    -0.71
    hart
    -0.71
    uve
    -0.69
    rera
    -0.67
    boat
    -0.66
    shore
    -0.66
    apo
    -0.65
     Developers
    -0.65
    POSITIVE LOGITS
     reprint
    1.13
     copies
    0.89
    ãĤ´
    0.86
    DragonMagazine
    0.84
     excerpts
    0.83
    rint
    0.83
    ="#
    0.82
     recol
    0.81
     reuse
    0.78
    ĸļ
    0.75
    Activations Density 0.029%

    No Known Activations