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

    Neuronpedia

    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. 6-RES-JB
    11. 7327
    Prev
    Next
    INDEX
    Explanations

    questions where the word "who" is followed by a verb or relates to the identity or actions of something

    oai_token-act-pair · gpt-3.5-turbo

    interrogative phrases that question identity or responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naissance
    -0.83
    ooters
    -0.72
     moot
    -0.68
    aneous
    -0.65
     cancellation
    -0.65
    vity
    -0.63
     Comprehensive
    -0.63
     Heights
    -0.62
    atform
    -0.60
     Reasons
    -0.60
    POSITIVE LOGITS
    wered
    0.69
     hect
    0.67
     Pearce
    0.66
     benefited
    0.66
    oa
    0.64
    opter
    0.64
     infiltrated
    0.63
     guessed
    0.62
    ?]
    0.62
     fault
    0.61
    Activations Density 0.106%

    No Known Activations