© 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. 22529
    Prev
    Next
    INDEX
    Explanations

    questions related to decision-making

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating relationships or connections

    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
    FIELD
    -0.62
    ICT
    -0.58
    estones
    -0.56
    onia
    -0.55
    inqu
    -0.55
    onte
    -0.54
    aditional
    -0.52
     necks
    -0.52
    itual
    -0.52
    rite
    -0.51
    POSITIVE LOGITS
     how
    1.80
     why
    1.75
     whence
    1.62
    why
    1.60
     what
    1.58
    what
    1.53
     WHY
    1.52
    how
    1.52
     HOW
    1.42
     WHAT
    1.40
    Activations Density 0.394%

    No Known Activations