© 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. 11-RES-JB
    11. 6972
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, sports terms, and economic/financial concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports, strategy, and economic factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     condem
    -0.65
     seated
    -0.58
     handwritten
    -0.56
     Boone
    -0.55
    PLIED
    -0.55
     routed
    -0.54
     redacted
    -0.54
     JFK
    -0.53
    oros
    -0.53
    stitial
    -0.52
    POSITIVE LOGITS
    âĢ
    0.92
     ASAP
    0.91
     sooner
    0.91
     lest
    0.84
    .�
    0.81
     altogether
    0.80
     anytime
    0.79
     indefinitely
    0.79
     âĢ
    0.77
     whilst
    0.77
    Activations Density 0.378%

    No Known Activations