© 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. 11-RES-JB
    11. 7520
    Prev
    Next
    INDEX
    Explanations

    instances of receiving or seeking feedback or responses

    oai_token-act-pair · gpt-3.5-turbo

    references to requests, responses, and the concept of coming back or returning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hemat
    -0.65
     Minimum
    -0.63
    é¾įå
    -0.59
    natureconservancy
    -0.57
    oint
    -0.57
    piring
    -0.55
    DonaldTrump
    -0.54
     Spread
    -0.53
    pmwiki
    -0.52
    icult
    -0.52
    POSITIVE LOGITS
     back
    2.35
     BACK
    1.85
    back
    1.81
     Back
    1.64
    Back
    1.62
     backs
    1.47
    backs
    1.46
    BACK
    1.33
     home
    1.16
     again
    1.12
    Activations Density 0.786%

    No Known Activations