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. 1-RES-JB
    6. 12383
    Prev
    Next
    INDEX
    Explanations

    references to disregarding or ignoring certain information or instructions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disregard or negligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oshenko
    -0.82
    izont
    -0.82
    ãĤ£
    -0.80
    izons
    -0.77
     mosqu
    -0.75
    iatus
    -0.72
    Afee
    -0.70
    ites
    -0.68
     Kov
    -0.66
    Ó
    -0.65
    POSITIVE LOGITS
    entimes
    0.84
    ortment
    0.81
    ulatory
    0.72
     sund
    0.70
    ulations
    0.69
    rule
    0.69
     ful
    0.68
    arding
    0.68
    bard
    0.68
    LESS
    0.67
    Activations Density 0.027%

    No Known Activations