© 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. 9-RES-JB
    11. 15895
    Prev
    Next
    INDEX
    Explanations

    language indicating focus on particular topics or questions

    oai_token-act-pair · gpt-3.5-turbo

    phrases introducing or referencing significant questions or topics

    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
    ahime
    -0.70
    aq
    -0.70
    ugu
    -0.69
    iola
    -0.62
    hent
    -0.61
    pling
    -0.60
    say
    -0.59
    aga
    -0.59
    usk
    -0.58
    onday
    -0.57
    POSITIVE LOGITS
     occurs
    1.07
     deserves
    1.05
     arises
    1.04
     begs
    1.02
     haun
    1.01
     ought
    1.01
     awaits
    1.00
     arose
    1.00
     happens
    0.99
     hasn
    0.97
    Activations Density 0.166%

    No Known Activations