© 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. 6-RES-JB
    11. 23701
    Prev
    Next
    INDEX
    Explanations

    references to academic journals

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific journals and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tall
    -0.69
    holders
    -0.69
    Lago
    -0.69
    ramid
    -0.69
     awoken
    -0.67
    rises
    -0.66
     cust
    -0.66
    chuk
    -0.64
    cream
    -0.64
    ranged
    -0.64
    POSITIVE LOGITS
     Proceedings
    0.95
    ournals
    0.95
     journal
    0.93
     PLoS
    0.92
    Paper
    0.91
     Pediatrics
    0.85
     papers
    0.85
    ļéĨĴ
    0.84
     Journals
    0.82
     journals
    0.79
    Activations Density 0.014%

    No Known Activations