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. 9534
    Prev
    Next
    INDEX
    Explanations

    details about specific individuals and their activities or associations

    oai_token-act-pair · gpt-3.5-turbo

    information related to sports players and their career events

    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
     ["
    -0.71
     [...]
    -0.68
    ...)
    -0.68
    hetic
    -0.67
    ]]
    -0.66
    â̦)
    -0.64
    Mods
    -0.62
     goddamn
    -0.62
    ."[
    -0.62
    Figure
    -0.62
    POSITIVE LOGITS
     controvers
    0.95
     criticised
    0.90
     controversial
    0.83
     embroiled
    0.78
     angered
    0.77
     ousted
    0.76
     outgoing
    0.76
     campaigner
    0.75
     outspoken
    0.74
     hotly
    0.74
    Activations Density 1.473%

    No Known Activations