© 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. 2-RES-JB
    11. 14580
    Prev
    Next
    INDEX
    Explanations

    legal or authorization-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with conflict and authority figures

    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
     Cosponsors
    -0.63
    anwhile
    -0.62
     Latest
    -0.61
    reporting
    -0.60
     Regions
    -0.60
    gov
    -0.55
     Infrastructure
    -0.54
     Proceedings
    -0.52
    arta
    -0.52
     Joint
    -0.51
    POSITIVE LOGITS
     vulner
    0.70
     toget
    0.66
    fuck
    0.61
     goodbye
    0.59
     whore
    0.58
     onstage
    0.58
     selves
    0.58
    .</
    0.56
    edIn
    0.56
     Saiyan
    0.55
    Activations Density 3.479%

    No Known Activations