© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 1484
    Prev
    Next
    INDEX
    Explanations

    comment-related phrases and keywords

    oai_token-act-pair · gpt-3.5-turbo

    references to comments, particularly in an online context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rescue
    -0.67
    fruit
    -0.66
    ccording
    -0.66
     Mysteries
    -0.66
     Recon
    -0.65
    rip
    -0.65
    duc
    -0.64
     Dresden
    -0.63
    isin
    -0.62
    red
    -0.62
    POSITIVE LOGITS
     comments
    1.07
     comment
    0.94
     commenters
    0.85
     remarks
    0.84
    comments
    0.84
     Comments
    0.82
     guiActiveUn
    0.80
    Comment
    0.80
    ariat
    0.79
     commenting
    0.78
    Activations Density 0.025%

    No Known Activations