© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4896
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "What do"

    oai_token-act-pair · gpt-3.5-turbo

    interrogative phrases that ask for opinions or information

    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
    fox
    -0.66
    WAYS
    -0.64
     Bridges
    -0.63
    mint
    -0.62
    legram
    -0.62
    agonists
    -0.61
    visory
    -0.61
    Dialogue
    -0.59
    boats
    -0.59
     Immunity
    -0.59
    POSITIVE LOGITS
    ?]
    0.80
    onga
    0.71
     wrong
    0.69
    omsday
    0.66
     transpired
    0.66
    ?),
    0.66
     includ
    0.63
     glean
    0.63
     happen
    0.62
     characterize
    0.62
    Activations Density 0.049%

    No Known Activations