© 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. 6994
    Prev
    Next
    INDEX
    Explanations

    quotations or reported speech

    oai_token-act-pair · gpt-3.5-turbo

    quoted statements and speech marks within the text

    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
     Creator
    -0.78
     XL
    -0.78
     Versus
    -0.77
     Wyn
    -0.76
     Clyde
    -0.75
     Cah
    -0.75
     paddle
    -0.75
     Hoy
    -0.75
     Isaac
    -0.75
     oy
    -0.74
    POSITIVE LOGITS
    significant
    1.87
    serious
    1.76
    extremely
    1.69
    reasonable
    1.68
    multiple
    1.67
    extreme
    1.67
    severe
    1.65
    very
    1.64
    extra
    1.63
    grave
    1.62
    Activations Density 0.130%

    No Known Activations