© 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. 4-RES-JB
    11. 4763
    Prev
    Next
    INDEX
    Explanations

    phrases related to news articles or headlines

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to current events and human rights issues

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

    No Comments

    Negative Logits
    itone
    -0.73
    idae
    -0.72
    venge
    -0.69
    phas
    -0.68
    Salt
    -0.68
    chuk
    -0.68
    mere
    -0.67
    hex
    -0.67
    Downloadha
    -0.66
    dn
    -0.66
    POSITIVE LOGITS
     REPORT
    1.28
     EDITION
    1.24
     FANTASY
    1.20
    MAN
    1.19
    LINE
    1.18
    OLOGY
    1.18
     OF
    1.18
    FIELD
    1.16
    WORK
    1.16
     VIDEOS
    1.16
    Activations Density 0.155%

    No Known Activations