© 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. 11-RES-JB
    11. 13961
    Prev
    Next
    INDEX
    Explanations

    occasional words or phrases related to events or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to frequency and occurrence of actions or events

    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
     Controls
    -0.91
    arts
    -0.91
    ources
    -0.90
    models
    -0.90
    values
    -0.86
    groups
    -0.85
    Sources
    -0.84
    levels
    -0.84
    apons
    -0.83
    sites
    -0.83
    POSITIVE LOGITS
     handshake
    1.34
     outburst
    1.31
     slap
    1.25
     announcement
    1.24
     swipe
    1.22
     remark
    1.22
     typo
    1.22
     apology
    1.21
     acknowledgment
    1.20
     acknowledgement
    1.20
    Activations Density 0.461%

    No Known Activations