© 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. 2628
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names and entities related to political news and events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the former president Trump in the context of criticism or controversy

    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
    ibility
    -0.68
    OWS
    -0.64
     Âł Âł
    -0.62
    ruary
    -0.61
     Oslo
    -0.60
     Generation
    -0.60
    ible
    -0.59
    dos
    -0.58
    SAM
    -0.57
    âĢİ
    -0.56
    POSITIVE LOGITS
     Kavanaugh
    0.62
     ordering
    0.58
     tariffs
    0.57
     len
    0.55
     tower
    0.54
     airstrike
    0.52
     convoy
    0.52
     unlocks
    0.52
     medd
    0.52
     condol
    0.52
    Activations Density 0.031%

    No Known Activations