© 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. 9896
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and risk assessment

    oai_token-act-pair · gpt-3.5-turbo

    references to treatments and their effectiveness or consequences

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    ï¸ı
    -0.68
    ãĥ©ãĥ³
    -0.64
    DragonMagazine
    -0.62
     )]
    -0.60
    gypt
    -0.60
    iane
    -0.57
    rious
    -0.53
     Bowen
    -0.52
     Sharma
    -0.52
    POSITIVE LOGITS
     at
    1.26
     altogether
    1.21
     whatsoever
    1.20
     simultaneously
    1.05
    At
    1.02
     concurrently
    0.99
     At
    0.97
    yet
    0.85
     respectively
    0.84
    at
    0.84
    Activations Density 0.770%

    No Known Activations