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. 8896
    Prev
    Next
    INDEX
    Explanations

    names, especially those that appear to be misspelled versions of the name "Dave"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the word "ave" and its variations, indicating a focus on averages or assessments

    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
    ually
    -0.71
    TY
    -0.68
    ION
    -0.67
    imation
    -0.67
    ItemThumbnailImage
    -0.63
    ARGET
    -0.63
    âĸ¬
    -0.63
    ion
    -0.62
    ional
    -0.62
    SN
    -0.61
    POSITIVE LOGITS
    llan
    1.01
    astern
    0.89
    tails
    0.78
    nesday
    0.78
    vine
    0.75
    tta
    0.75
    tsky
    0.74
    ornings
    0.74
    aways
    0.74
    dit
    0.73
    Activations Density 0.020%

    No Known Activations