© 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. 24478
    Prev
    Next
    INDEX
    Explanations

    sequences of characters that don't form coherent words or phrases, with occasional appearances of medical terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of strong emotions and reactions

    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
    Kenn
    -0.90
     Clement
    -0.85
     McL
    -0.83
    CL
    -0.80
     Doll
    -0.79
     Kenn
    -0.77
     Kro
    -0.76
     Kennedy
    -0.76
    wcsstore
    -0.76
     Kern
    -0.75
    POSITIVE LOGITS
    +
    1.11
    +++
    1.09
    +,
    1.06
    +.
    0.99
    +)
    0.95
    ive
    0.94
    plus
    0.92
    aina
    0.89
    ++
    0.85
    active
    0.85
    Activations Density 0.330%

    No Known Activations