© 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. 21575
    Prev
    Next
    INDEX
    Explanations

    concepts related to politics and policies

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to political and social issues

    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
    obic
    -0.65
    assian
    -0.64
    umo
    -0.63
     charm
    -0.60
    otted
    -0.59
    onym
    -0.59
     clot
    -0.58
     taco
    -0.58
     laugh
    -0.58
    guyen
    -0.58
    POSITIVE LOGITS
     alike
    0.94
    making
    0.91
    flows
    0.88
    smanship
    0.86
     trends
    0.85
     outcomes
    0.83
     worldwide
    0.81
     decisions
    0.80
     processes
    0.80
     endeavors
    0.79
    Activations Density 0.347%

    No Known Activations