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

    Neuronpedia

    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. 3-RES-JB
    11. 565
    Prev
    Next
    INDEX
    Explanations

    references to written articles or blog posts

    oai_token-act-pair · gpt-3.5-turbo

    references to articles or statements on recent events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.57
    peat
    -0.54
    angs
    -0.51
     condos
    -0.50
     chopping
    -0.49
     Saiyan
    -0.48
     annihil
    -0.48
     peas
    -0.48
    tackle
    -0.47
     decaying
    -0.47
    POSITIVE LOGITS
     redacted
    0.70
     quoting
    0.65
     quoted
    0.63
    reports
    0.63
     publication
    0.58
     quotation
    0.57
     cited
    0.57
     quotations
    0.57
     archive
    0.55
    published
    0.55
    Activations Density 3.307%

    No Known Activations