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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13906
    Prev
    Next
    INDEX
    Explanations

    numerical figures, like counts, years, and quantities

    oai_token-act-pair · gpt-3.5-turbo

    counts or quantities related to legal charges or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illet
    -0.78
    Reviewer
    -0.71
    tick
    -0.69
    cture
    -0.69
    atican
    -0.65
    brand
    -0.63
     rite
    -0.63
    BuyableInstoreAndOnline
    -0.62
    gerald
    -0.62
    bard
    -0.62
    POSITIVE LOGITS
     consequ
    0.92
     importantly
    0.86
     subsequent
    0.86
     accompanying
    0.85
     ensuing
    0.81
     others
    0.78
     respectively
    0.78
     versa
    0.76
     thereof
    0.74
     consequently
    0.73
    Activations Density 0.268%

    No Known Activations