© 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 EvalsExportsinterp-engineNEWAPI 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. 16310
    Prev
    Next
    INDEX
    Explanations

    professionals and roles within various fields of work

    oai_token-act-pair · gpt-3.5-turbo

    titles or roles related to individuals in various professional or authoritative capacities

    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
     dots
    -0.70
    ptions
    -0.68
     underlying
    -0.64
    sing
    -0.62
     everlasting
    -0.61
    plets
    -0.59
    ansk
    -0.59
     disparate
    -0.59
     occupants
    -0.58
    encers
    -0.58
    POSITIVE LOGITS
    enegger
    0.74
     whose
    0.73
     specializing
    0.70
     who
    0.69
     named
    0.69
     staffer
    0.69
     laureate
    0.67
     whom
    0.66
     researcher
    0.65
    hunter
    0.65
    Activations Density 0.297%

    No Known Activations