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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 23270
    Prev
    Next
    INDEX
    Explanations

    Twitter handles preceded by "@" symbol

    oai_token-act-pair · gpt-3.5-turbo

    social media handles or mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specificity
    -0.81
     ÂŃ
    -0.74
     submarines
    -0.73
     influenza
    -0.72
     favor
    -0.72
     tape
    -0.71
     SEAL
    -0.71
     margins
    -0.71
     loans
    -0.71
     compress
    -0.70
    POSITIVE LOGITS
    Real
    1.39
    thereal
    1.35
    Official
    1.27
    Coach
    1.26
    dan
    1.25
    realDonaldTrump
    1.23
    username
    1.20
    jac
    1.19
    mc
    1.19
    greg
    1.18
    Activations Density 0.020%

    No Known Activations