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. 7890
    Prev
    Next
    INDEX
    Explanations

    specific mentions of labeling, especially in relation to food, products, or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of labeling, particularly regarding food and products

    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
    --+
    -0.77
    ----------------
    -0.69
     Hitchcock
    -0.68
    itars
    -0.68
    aldo
    -0.66
     Fri
    -0.66
    Es
    -0.64
     Oaks
    -0.64
     Hiroshima
    -0.63
     Emir
    -0.63
    POSITIVE LOGITS
     labels
    1.12
     labeling
    1.11
     labelled
    0.86
     label
    0.84
    furt
    0.83
     labeled
    0.81
    uggest
    0.80
    ovo
    0.77
    liga
    0.75
    amine
    0.74
    Activations Density 0.007%

    No Known Activations