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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 1490
    Prev
    Next
    INDEX
    Explanations

    mentions of academic publishing, including terms like "peer-reviewed," "journal," and "published."

    oai_token-act-pair · gpt-3.5-turbo

    references to academic publishing, particularly in peer-reviewed journals

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

    No Comments

    Negative Logits
     charms
    -0.76
    Lago
    -0.71
    xit
    -0.70
    lt
    -0.69
    quer
    -0.68
    hd
    -0.68
    forced
    -0.68
    jer
    -0.68
    tones
    -0.66
     Stronghold
    -0.65
    POSITIVE LOGITS
    ournals
    0.97
     biomedical
    0.96
     PubMed
    0.91
     journal
    0.88
     peer
    0.86
     literature
    0.86
    doi
    0.85
     citation
    0.85
     journals
    0.85
     manuscript
    0.85
    Activations Density 0.142%

    No Known Activations