© 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. 8-RES-JB
    11. 6105
    Prev
    Next
    INDEX
    Explanations

    mentions of political independence movements and referendums

    oai_token-act-pair · gpt-3.5-turbo

    references to independence movements or the concept of independence itself

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bilt
    -0.79
    enegger
    -0.79
    geries
    -0.71
    ergy
    -0.70
    opa
    -0.69
    geon
    -0.68
    eor
    -0.67
    nos
    -0.66
     Insect
    -0.64
    ãĥ¥
    -0.64
    POSITIVE LOGITS
     referendum
    1.05
     oath
    0.84
     Catalonia
    0.78
    yip
    0.76
    arta
    0.72
    ederation
    0.71
    uesday
    0.70
     independence
    0.67
    eas
    0.66
    inally
    0.66
    Activations Density 0.033%

    No Known Activations