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. 19034
    Prev
    Next
    INDEX
    Explanations

    technical bug fixes and software updates

    oai_token-act-pair · gpt-3.5-turbo

    references to bugs and exploits in software systems

    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
    é¾
    -0.84
    books
    -0.79
    anooga
    -0.78
    tainment
    -0.73
    acebook
    -0.73
    SPONSORED
    -0.73
    —-
    -0.71
    Educ
    -0.70
    llah
    -0.70
    "—
    -0.68
    POSITIVE LOGITS
     tooltip
    1.09
     overwrite
    1.05
     GUI
    0.98
     respawn
    0.97
     UI
    0.94
     plugin
    0.89
     override
    0.88
     Texture
    0.84
     disable
    0.84
     shader
    0.84
    Activations Density 0.359%

    No Known Activations