© 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. 21555
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations, events, or individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of organizations and institutions

    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
    Ü
    -0.67
    animate
    -0.65
    Ĥ
    -0.65
    ãĤ¹
    -0.62
    é¾įå
    -0.61
    ãĥij
    -0.61
    ľ
    -0.60
    ¯
    -0.60
    Ŀ
    -0.59
    ÃįÃį
    -0.59
    POSITIVE LOGITS
     discusses
    1.41
     announces
    1.15
     testified
    1.14
     commented
    1.14
     joins
    1.13
     agrees
    1.12
     speaks
    1.11
     attends
    1.10
     welcomes
    1.10
     says
    1.07
    Activations Density 0.371%

    No Known Activations