© 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. 4-RES-JB
    11. 15445
    Prev
    Next
    INDEX
    Explanations

    word sequences containing the question "What are"

    oai_token-act-pair · gpt-3.5-turbo

    questions that begin with "what are" or similar phrases indicating inquiry

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

    No Comments

    Negative Logits
    dom
    -0.88
    oire
    -0.82
    speak
    -0.80
    icism
    -0.80
    osate
    -0.75
    iasis
    -0.69
    ileaks
    -0.68
    antry
    -0.67
    town
    -0.67
    ocracy
    -0.65
    POSITIVE LOGITS
    wolves
    1.16
    senal
    0.97
    wolf
    0.93
    nt
    0.78
    nda
    0.76
     legion
    0.70
     gonna
    0.67
     sequels
    0.65
    nd
    0.65
     snapshots
    0.65
    Activations Density 0.199%

    No Known Activations