© 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. 11-RES-JB
    11. 14860
    Prev
    Next
    INDEX
    Explanations

    noun phrases starting with "combined with" or "taken together" to indicate a cumulative effect

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of combination or conjunction

    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
    keeper
    -0.74
    article
    -0.67
    ond
    -0.66
     livest
    -0.65
     Passage
    -0.65
    holes
    -0.65
    keepers
    -0.64
    blers
    -0.61
    cards
    -0.61
    ighth
    -0.60
    POSITIVE LOGITS
     together
    0.78
     with
    0.74
    ãĤ¤ãĥĪ
    0.70
    amorph
    0.63
     into
    0.63
     efforts
    0.63
     disparate
    0.62
     oppos
    0.61
    atively
    0.60
    handled
    0.60
    Activations Density 0.066%

    No Known Activations