© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6260
    Prev
    Next
    INDEX
    Explanations

    questions or clauses using the word "how"

    oai_token-act-pair · gpt-3.5-turbo

    questions and phrases that begin with "how."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     atop
    -0.58
     out
    -0.57
     stands
    -0.56
     electrodes
    -0.54
     base
    -0.53
     Nam
    -0.53
     Met
    -0.52
     constrained
    -0.52
     majority
    -0.51
     root
    -0.51
    POSITIVE LOGITS
    how
    4.26
    HOW
    2.06
    why
    1.74
    what
    1.52
    where
    1.44
    How
    1.41
    who
    1.35
     HOW
    1.32
    whether
    1.30
     how
    1.24
    Activations Density 0.009%

    No Known Activations