© 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. 8-RES-JB
    11. 19384
    Prev
    Next
    INDEX
    Explanations

    the verb "bother" in relation to the action or lack of action following it

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "bother" and its variations, indicating a focus on issues of effort and neglect

    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
    uts
    -0.83
    oiler
    -0.77
    reements
    -0.76
    urst
    -0.75
    obal
    -0.73
    RNA
    -0.72
     Blueprint
    -0.71
    arb
    -0.71
    uti
    -0.70
    rats
    -0.70
    POSITIVE LOGITS
     bothering
    1.00
     bother
    0.93
    some
    0.90
     bothered
    0.83
    crow
    0.69
     Gaal
    0.68
     paying
    0.67
    lessly
    0.66
    fulness
    0.66
    ktop
    0.65
    Activations Density 0.036%

    No Known Activations