© 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. 6927
    Prev
    Next
    INDEX
    Explanations

    words related to quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to providing additional features or enhancements

    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
     Outbreak
    -0.88
     Deaths
    -0.66
     Ending
    -0.65
    REDACTED
    -0.65
    released
    -0.64
    ©¶æ
    -0.63
     incorrectly
    -0.63
    meet
    -0.63
     nicknamed
    -0.62
    ģ«
    -0.62
    POSITIVE LOGITS
     flexibility
    1.76
     versatility
    1.59
     freedom
    1.33
     functionality
    1.30
     customization
    1.29
     latitude
    1.20
     possibilities
    1.18
     usefulness
    1.18
     advantages
    1.17
     depth
    1.17
    Activations Density 0.238%

    No Known Activations