© 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. 3174
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or commands

    oai_token-act-pair · gpt-3.5-turbo

    numeric or coded time-related indicators

    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
    ittal
    -0.79
    quartered
    -0.70
    ipe
    -0.65
    ichick
    -0.64
    ecd
    -0.62
    iste
    -0.60
    aird
    -0.60
    lez
    -0.60
    fter
    -0.59
    ery
    -0.59
    POSITIVE LOGITS
     EDITION
    1.34
     STORY
    1.24
    WOR
    1.22
    WORK
    1.18
    OUT
    1.16
    MEN
    1.15
     REPORT
    1.15
    LET
    1.13
    CLASS
    1.13
    DAY
    1.12
    Activations Density 0.228%

    No Known Activations