Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 15088
    Prev
    Next
    INDEX
    Explanations

    questions or requests for information

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "any" in various contexts

    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
    rex
    -0.70
    seless
    -0.70
    ually
    -0.57
    endas
    -0.57
     wills
    -0.57
    staking
    -0.57
    bows
    -0.56
     floods
    -0.55
    ward
    -0.55
    ulo
    -0.54
    POSITIVE LOGITS
    THING
    1.43
    body
    0.96
    WHERE
    0.95
    thin
    0.94
    ONE
    0.91
    place
    0.90
    where
    0.88
     semblance
    0.81
    MORE
    0.79
     indication
    0.78
    Activations Density 0.075%

    No Known Activations