© 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. 18649
    Prev
    Next
    INDEX
    Explanations

    data points such as statistics, numbers, and figures

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data points related to various statistics and demographics

    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
    inventoryQuantity
    -0.83
    rette
    -0.80
    catentry
    -0.75
    endif
    -0.73
    asso
    -0.69
    Others
    -0.69
    ãĤ´ãĥ³
    -0.68
    potion
    -0.66
    ror
    -0.66
    bol
    -0.63
    POSITIVE LOGITS
     total
    1.15
     377
    0.90
     294
    0.86
     371
    0.84
     2014
    0.84
     2011
    0.83
     254
    0.83
     224
    0.82
     2015
    0.82
     338
    0.81
    Activations Density 0.270%

    No Known Activations