© 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. 4-RES-JB
    11. 17013
    Prev
    Next
    INDEX
    Explanations

    phrases related to old-school concepts or items

    oai_token-act-pair · gpt-3.5-turbo

    references to "old school" concepts or elements

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

    No Comments

    Negative Logits
    OPLE
    -0.78
     Bundy
    -0.75
     Bots
    -0.69
    TN
    -0.67
     Cabrera
    -0.63
     candidacy
    -0.62
     Ventura
    -0.61
     tame
    -0.60
     LIVE
    -0.59
     contiguous
    -0.59
    POSITIVE LOGITS
    kids
    1.16
    girls
    1.08
    boy
    1.07
    boys
    1.00
    children
    0.99
    girl
    0.98
    kid
    0.97
    masters
    0.97
    master
    0.87
    child
    0.84
    Activations Density 0.053%

    No Known Activations