© 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. 891
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities being involved with certain actions or events

    oai_token-act-pair · gpt-3.5-turbo

    end-of-text markers

    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
    Side
    -0.42
    edIn
    -0.41
    inav
    -0.40
    ï
    -0.36
    regate
    -0.36
    itiveness
    -0.36
    Make
    -0.35
    ucc
    -0.35
    heny
    -0.35
    Gre
    -0.34
    POSITIVE LOGITS
     incapable
    0.60
     unable
    0.59
     able
    0.58
     gonna
    0.57
     supposed
    0.57
     obliged
    0.57
     deprecated
    0.55
     rated
    0.55
     obligated
    0.55
     pleased
    0.54
    Activations Density 0.684%

    No Known Activations