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. 6-RES-JB
    6. 21700
    Prev
    Next
    INDEX
    Explanations

    names of individuals and groups involved in conflicts or political situations

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the surname "al" indicating Middle Eastern identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.76
     Pixar
    -0.72
     TTC
    -0.70
    ERN
    -0.69
    EEE
    -0.69
     BART
    -0.68
     Cricket
    -0.68
    roid
    -0.68
     REPL
    -0.68
    IELD
    -0.67
    POSITIVE LOGITS
    ham
    0.92
     Qaeda
    0.90
     Islam
    0.88
    aida
    0.87
    manac
    0.86
    aina
    0.85
    hari
    0.84
    Qaeda
    0.84
    uded
    0.82
    ayn
    0.82
    Activations Density 0.030%

    No Known Activations