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. 16616
    Prev
    Next
    INDEX
    Explanations

    the word "Rogue" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    the term "rogue" and its variations in different contexts

    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
    ori
    -0.80
    atsu
    -0.77
    ieu
    -0.77
    drops
    -0.76
    rix
    -0.76
    emporary
    -0.75
    iences
    -0.73
    odium
    -0.71
    ulty
    -0.70
    urity
    -0.70
    POSITIVE LOGITS
    ^^^^
    0.79
     Trader
    0.74
     trooper
    0.71
     rogue
    0.71
    esses
    0.69
     Squadron
    0.68
     trader
    0.68
    hun
    0.67
     thumb
    0.66
     rend
    0.63
    Activations Density 0.022%

    No Known Activations