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. 9-RES-JB
    6. 775
    Prev
    Next
    INDEX
    Explanations

    references to specific websites and articles

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant keywords or phrases related to media and publication references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.98
     guiName
    -0.89
    ãĢİ
    -0.84
    âĵĺ
    -0.68
    »Ĵ
    -0.68
    sbm
    -0.68
    foreseen
    -0.65
     (?,
    -0.65
    ãĢIJ
    -0.65
    ":{"
    -0.64
    POSITIVE LOGITS
    .)
    1.72
    !)
    1.68
    ?)
    1.67
    )"
    1.64
    â̦)
    1.59
     .)
    1.56
    )."
    1.54
    ...)
    1.49
    *)
    1.47
    .")
    1.45
    Activations Density 0.262%

    No Known Activations