© 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. 10242
    Prev
    Next
    INDEX
    Explanations

    seem to be numerical patterns or sequences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "order" used in various contexts

    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
    vae
    -0.88
    peria
    -0.78
    ipedia
    -0.77
    lasses
    -0.75
    rities
    -0.75
    reath
    -0.73
    espie
    -0.72
    abies
    -0.71
    attery
    -0.69
    practice
    -0.69
    POSITIVE LOGITS
    lies
    1.29
    liness
    1.20
    eering
    0.92
    book
    0.83
     cancell
    0.81
     fulfillment
    0.79
    books
    0.73
     Mant
    0.72
     issued
    0.72
     fulfilled
    0.72
    Activations Density 0.053%

    No Known Activations