© 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. 3-RES-JB
    11. 4313
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "screw" with varying intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "screw" and its related forms indicating frustration or mistakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åī
    -0.78
    icipated
    -0.72
    usable
    -0.71
    rouse
    -0.70
    CVE
    -0.69
    govtrack
    -0.67
    CTV
    -0.64
     è£ıç
    -0.64
    ISSION
    -0.63
    anamo
    -0.62
    POSITIVE LOGITS
    driver
    1.14
    drivers
    1.00
     Whedon
    0.97
     screws
    0.96
     screw
    0.93
     screwed
    0.91
    hole
    0.87
    holes
    0.83
    bol
    0.77
     fucked
    0.75
    Activations Density 0.014%

    No Known Activations