© 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. 9-RES-JB
    11. 4811
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and government officials

    oai_token-act-pair · gpt-3.5-turbo

    political or government-related names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iencies
    -0.73
    abases
    -0.62
     havoc
    -0.62
     distinctions
    -0.61
     yuan
    -0.57
    aido
    -0.56
    lder
    -0.55
     bets
    -0.54
     distinction
    -0.54
     burgers
    -0.54
    POSITIVE LOGITS
     informing
    1.14
     stating
    1.13
     indicating
    1.12
     outlining
    1.11
     detailing
    1.11
     wherein
    1.07
     concerning
    1.06
     regarding
    1.03
     Regarding
    1.02
     describing
    1.01
    Activations Density 0.607%

    No Known Activations