Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 9279
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of action or effort

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bother."

    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
    uts
    -0.89
    oiler
    -0.86
    arta
    -0.84
    arb
    -0.79
    RNA
    -0.76
    urst
    -0.75
    INAL
    -0.74
    sung
    -0.74
    reements
    -0.73
    obal
    -0.73
    POSITIVE LOGITS
     bother
    1.04
     bothering
    0.99
    some
    0.97
     bothered
    0.80
    crow
    0.79
     Gaal
    0.72
    fulness
    0.68
    ingly
    0.66
    lessly
    0.65
    bear
    0.63
    Activations Density 0.022%

    No Known Activations