© 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. 24077
    Prev
    Next
    INDEX
    Explanations

    large numbers expressed in a specific format, usually involving commas

    oai_token-act-pair · gpt-3.5-turbo

    numerical values indicating counts or quantities

    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
     Painter
    -0.62
     sidel
    -0.57
    Anyway
    -0.55
    alsh
    -0.55
     Elys
    -0.53
    ËĪ
    -0.52
     Narr
    -0.52
    surv
    -0.51
    anus
    -0.51
    hess
    -0.50
    POSITIVE LOGITS
     million
    1.10
     000
    1.06
     thousand
    1.02
    %"
    1.01
     lakh
    0.99
    00
    0.94
     MILL
    0.94
    million
    0.92
     billion
    0.92
    00000
    0.91
    Activations Density 0.138%

    No Known Activations