© 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. 6030
    Prev
    Next
    INDEX
    Explanations

    informaton relevant to politicians, political events and manifestos in the context of European countries, such as Britain

    oai_token-act-pair · gpt-3.5-turbo

    names and titles related to political figures and events

    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
    ndum
    -0.74
    emale
    -0.69
    ategory
    -0.64
    imer
    -0.62
    peria
    -0.61
    oldemort
    -0.61
    alog
    -0.59
    olson
    -0.58
    aples
    -0.58
    ulton
    -0.57
    POSITIVE LOGITS
     Getty
    0.73
     è£ıè
    0.67
     RTX
    0.67
    ãģ®å
    0.67
     domains
    0.66
    åij
    0.66
     domain
    0.65
    Heart
    0.65
    èĪ
    0.64
    entimes
    0.64
    Activations Density 0.109%

    No Known Activations