© 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. 23151
    Prev
    Next
    INDEX
    Explanations

    news article snippets related to governmental and company activities

    oai_token-act-pair · gpt-3.5-turbo

    references to studies, research publications, and institutional reports

    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
     payoff
    -0.52
     argument
    -0.52
     misconception
    -0.51
    onom
    -0.51
     repetition
    -0.51
     trickle
    -0.50
     depends
    -0.50
    ogeneity
    -0.50
     econom
    -0.50
     instinct
    -0.50
    POSITIVE LOGITS
     respectively
    0.75
    ornings
    0.69
    zona
    0.68
    ĪĴ
    0.63
    soDeliveryDate
    0.59
    emale
    0.59
    illac
    0.58
     headquartered
    0.56
    onductor
    0.56
    ornia
    0.56
    Activations Density 2.924%

    No Known Activations