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. 14324
    Prev
    Next
    INDEX
    Explanations

    percentage values related to statistics or public opinion

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics or percentages related to public opinion

    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
    DragonMagazine
    -0.75
    piracy
    -0.71
    Reviewer
    -0.70
    ipment
    -0.70
    aviour
    -0.66
     vend
    -0.64
    uyomi
    -0.64
     exposition
    -0.62
    ffen
    -0.62
     pri
    -0.61
    POSITIVE LOGITS
     percent
    1.16
    %
    1.15
    %-
    1.13
    %;
    1.10
    %,
    1.10
    %.
    1.09
    %:
    1.03
    %),
    0.98
    %)
    0.98
    %).
    0.97
    Activations Density 0.281%

    No Known Activations