© 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. 22645
    Prev
    Next
    INDEX
    Explanations

    mentions of large sums of money or quantities

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings and punctuation

    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
     volunte
    -0.95
     satell
    -0.93
     carbohyd
    -0.91
     challeng
    -0.86
     exting
    -0.86
     teasp
    -0.83
    ascus
    -0.81
     suspic
    -0.81
     tremend
    -0.80
     tradem
    -0.79
    POSITIVE LOGITS
     Whether
    1.16
     Though
    1.14
     Considering
    1.14
     While
    1.14
     Although
    1.12
     Assuming
    1.11
     Presumably
    1.10
     Fortunately
    1.09
     According
    1.09
     Granted
    1.09
    Activations Density 0.601%

    No Known Activations