© 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. 2-RES-JB
    11. 17272
    Prev
    Next
    INDEX
    Explanations

    references to screws, both the object and the action of screwing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "screw" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usable
    -0.68
    rouse
    -0.67
    HCR
    -0.64
    outh
    -0.62
    ciplinary
    -0.62
    CHR
    -0.62
     Latvia
    -0.62
    CVE
    -0.61
    åī
    -0.61
    govtrack
    -0.61
    POSITIVE LOGITS
    driver
    1.18
     screws
    1.13
     screw
    1.04
    drivers
    1.02
    hole
    0.86
     screwed
    0.85
     Whedon
    0.84
     Screw
    0.84
    holes
    0.78
    ritten
    0.76
    Activations Density 0.009%

    No Known Activations