© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 8759
    Prev
    Next
    INDEX
    Explanations

    words related to screwing or messing up

    oai_token-act-pair · gpt-3.5-turbo

    references to mistakes or failures, often using the metaphor of "screwing up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åī
    -0.85
    vation
    -0.79
    usable
    -0.75
    cki
    -0.67
    ãĥ´
    -0.66
    λ
    -0.66
    ve
    -0.65
    ãĤ³
    -0.64
    DragonMagazine
    -0.64
    omas
    -0.64
    POSITIVE LOGITS
    driver
    1.47
    drivers
    1.33
    hole
    0.98
    holes
    0.87
    ritten
    0.87
     Whedon
    0.85
    engers
    0.83
    ball
    0.80
    bol
    0.80
     screws
    0.78
    Activations Density 0.026%

    No Known Activations