© 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. 8-RES-JB
    11. 19292
    Prev
    Next
    INDEX
    Explanations

    words related to emphasizing or repeating information

    oai_token-act-pair · gpt-3.5-turbo

    instances of emphasizing, reiterating, and corroborating information

    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
     Grail
    -0.68
    RAW
    -0.64
    farm
    -0.64
     pecul
    -0.63
    AFTA
    -0.63
     Typhoon
    -0.63
     Eye
    -0.62
    soever
    -0.62
     Surv
    -0.59
     blindly
    -0.59
    POSITIVE LOGITS
    uating
    1.37
    uation
    1.31
    uated
    1.28
    ating
    1.25
    uations
    1.24
    idated
    1.23
    ation
    1.19
    ued
    1.17
    uates
    1.16
    uing
    1.15
    Activations Density 0.085%

    No Known Activations