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. 10-RES-JB
    6. 391
    Prev
    Next
    INDEX
    Explanations

    statements about facts or truths

    oai_token-act-pair · gpt-3.5-turbo

    statements emphasizing the truth or reality of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     livest
    -0.72
    ascus
    -0.67
    dain
    -0.63
     streng
    -0.62
    vantage
    -0.61
     redes
    -0.60
    ModLoader
    -0.59
     administ
    -0.59
    /**
    -0.57
    incinn
    -0.56
    POSITIVE LOGITS
    uality
    1.13
     that
    1.07
    orial
    1.00
    ually
    0.99
    ional
    0.98
    that
    0.86
    oids
    0.86
    oid
    0.83
     THAT
    0.80
    itious
    0.76
    Activations Density 0.034%

    No Known Activations