Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14620
    Prev
    Next
    INDEX
    Explanations

    names of individuals, specifically Alexis and Petraeus

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly in the context of political or notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spring
    -1.04
    FU
    -1.02
    shaw
    -0.93
    bid
    -0.82
    ITNESS
    -0.78
    ned
    -0.76
    Indiana
    -0.74
    SourceFile
    -0.72
    ×Ļ×
    -0.72
    sole
    -0.72
    POSITIVE LOGITS
     Alexis
    1.37
     mosqu
    1.11
     metic
    0.90
     mathemat
    0.79
    uries
    0.79
     Wenger
    0.76
     suspic
    0.75
     Olivier
    0.75
     Sanchez
    0.74
     traged
    0.73
    Activations Density 0.009%

    No Known Activations