© 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. 15728
    Prev
    Next
    INDEX
    Explanations

    information related to abortion statistics and demographics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to statistical rates expressed as "per" followed by numerical values

    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
    inders
    -0.72
    achine
    -0.67
    downs
    -0.67
    ForgeModLoader
    -0.66
    Stretch
    -0.64
    bugs
    -0.63
     Tactics
    -0.63
    aways
    -0.63
    hess
    -0.63
    Clar
    -0.62
    POSITIVE LOGITS
     capita
    1.57
     thousand
    1.10
     person
    1.01
     100
    0.98
     million
    0.98
     inhabit
    0.97
     1000
    0.97
     hundred
    0.94
     ann
    0.92
     lakh
    0.90
    Activations Density 0.039%

    No Known Activations