© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4097
    Prev
    Next
    INDEX
    Explanations

    texts related to technical instructions or programming commands

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    information related to deployment processes and user interaction in technology contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    BuyableInstoreAndOnline
    -0.52
    udder
    -0.51
    oubted
    -0.44
    idable
    -0.44
    ĪĴ
    -0.43
    Interstitial
    -0.42
    cknowled
    -0.41
    riv
    -0.39
    continue
    -0.39
     nuances
    -0.39
    POSITIVE LOGITS
    :
    1.87
    .):
    1.78
    :-
    1.74
    %:
    1.74
    .:
    1.74
    *:
    1.74
    !:
    1.73
    ':
    1.72
    ?:
    1.69
    :[
    1.68
    Activations Density 1.560%

    No Known Activations