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. 17389
    Prev
    Next
    INDEX
    Explanations

    technical or policy-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various societal issues and conditions

    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
     Defin
    -0.62
    ©¶æ
    -0.55
     suffice
    -0.53
    é¾įå
    -0.50
    è¦ļéĨĴ
    -0.50
    Ĭ±
    -0.49
    ttle
    -0.48
     Pixie
    -0.48
    £ı
    -0.48
     lockout
    -0.47
    POSITIVE LOGITS
    wise
    0.57
    aila
    0.51
     etc
    0.49
    tis
    0.46
    viol
    0.44
    oday
    0.44
    )!
    0.44
     extraord
    0.44
    LP
    0.44
    ax
    0.43
    Activations Density 0.582%

    No Known Activations