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. 4297
    Prev
    Next
    INDEX
    Explanations

    numbers representing percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or percentages referenced in the text

    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
    ettings
    -0.71
    Fram
    -0.70
    par
    -0.67
    medi
    -0.63
    hammad
    -0.62
     redemption
    -0.61
    ramid
    -0.61
    quet
    -0.60
    henko
    -0.60
    que
    -0.59
    POSITIVE LOGITS
    %"
    1.19
    %
    1.16
     percent
    1.12
    %.
    1.07
    %-
    1.07
    %:
    1.00
    %;
    0.99
     Minutes
    0.98
    %,
    0.98
     minutes
    0.96
    Activations Density 0.140%

    No Known Activations