© 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. 4-RES-JB
    11. 17011
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of bothering or not bothering someone is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bother" and its variations, indicating a focus on lack of effort or concern

    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
    arb
    -0.77
    arta
    -0.77
    INAL
    -0.77
    oiler
    -0.75
    ramer
    -0.74
    UE
    -0.74
    ophe
    -0.73
    sung
    -0.72
    inia
    -0.69
    odes
    -0.68
    POSITIVE LOGITS
     bother
    1.17
     bothering
    1.06
    some
    0.90
    crow
    0.89
     bothered
    0.82
    MENTS
    0.80
     bothers
    0.71
     tamp
    0.68
    fulness
    0.65
     Ivanka
    0.64
    Activations Density 0.016%

    No Known Activations