© 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. 8-RES-JB
    11. 22353
    Prev
    Next
    INDEX
    Explanations

    instances where the term "cap" is used

    oai_token-act-pair · gpt-3.5-turbo

    references to "cap" or "capacity" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bread
    -0.70
     anten
    -0.69
    ĪĴ
    -0.69
    issance
    -0.65
    hower
    -0.64
    isance
    -0.63
     Roses
    -0.61
    cause
    -0.61
     Modes
    -0.60
     Fres
    -0.59
    POSITIVE LOGITS
    itol
    1.48
    uchin
    1.11
    aic
    1.03
    rice
    1.02
    illary
    1.01
    itals
    0.93
    stan
    0.92
    rices
    0.92
    nea
    0.92
    rison
    0.88
    Activations Density 0.024%

    No Known Activations