© 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. 4-RES-JB
    11. 21971
    Prev
    Next
    INDEX
    Explanations

    phrases related to cutting or disconnecting something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "cut off."

    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
    inx
    -0.71
    nesday
    -0.70
    xtap
    -0.69
    ENG
    -0.69
     teasp
    -0.67
    itely
    -0.67
    anners
    -0.64
    swick
    -0.63
    inks
    -0.63
    FUL
    -0.61
    POSITIVE LOGITS
    ment
    0.68
    pring
    0.67
    screen
    0.66
    rollment
    0.64
    course
    0.63
     course
    0.61
     shore
    0.61
     bridges
    0.60
     landfall
    0.60
    river
    0.60
    Activations Density 0.013%

    No Known Activations