© 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. 10-RES-JB
    11. 10773
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal disclaimers and permissions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to disclaimers and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÙĴ
    -0.78
    Ò
    -0.71
    Suddenly
    -0.64
    apon
    -0.64
     Suddenly
    -0.64
    abuse
    -0.63
    perse
    -0.62
    rolet
    -0.61
    chant
    -0.61
    tackle
    -0.61
    POSITIVE LOGITS
     contents
    1.17
     following
    1.08
     foregoing
    1.05
     information
    0.95
     remainder
    0.95
     opinions
    0.93
    atre
    0.93
     above
    0.88
     purpose
    0.88
    oret
    0.87
    Activations Density 0.266%

    No Known Activations