© 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. 4-RES-JB
    11. 10604
    Prev
    Next
    INDEX
    Explanations

    phrases related to reactions or replies in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "response" and variations indicating replies or reactions to events or statements

    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
    rome
    -0.77
    ffe
    -0.70
    cutting
    -0.69
     knots
    -0.68
    hemat
    -0.67
    ramer
    -0.66
    fo
    -0.65
    rust
    -0.64
    roots
    -0.63
    bound
    -0.63
    POSITIVE LOGITS
     thereto
    1.00
     response
    1.00
     responses
    0.91
     reaction
    0.88
    response
    0.82
     reply
    0.81
     respond
    0.79
     Response
    0.78
    reply
    0.77
    DragonMagazine
    0.77
    Activations Density 0.030%

    No Known Activations