© 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. 9-RES-JB
    11. 22648
    Prev
    Next
    INDEX
    Explanations

    phrases related to requests for comments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of requests for comments or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bleacher
    -0.70
     disgr
    -0.69
    gra
    -0.65
     deprived
    -0.64
     annoy
    -0.64
    Ļ½
    -0.64
    paces
    -0.63
    hess
    -0.62
    iah
    -0.61
    ware
    -0.61
    POSITIVE LOGITS
     comment
    1.52
     clarification
    1.30
     comments
    1.06
     explanation
    1.05
     explanations
    1.04
     answers
    1.04
    comment
    0.96
     interviews
    0.95
     details
    0.91
     insight
    0.91
    Activations Density 0.092%

    No Known Activations