© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 13532
    Prev
    Next
    INDEX
    Explanations

    dates and actions related to being appointed, elected, or hired

    oai_token-act-pair · gpt-3.5-turbo

    words associated with political appointments and elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ggles
    -0.63
    rouse
    -0.62
    some
    -0.60
    enance
    -0.60
    orians
    -0.59
    gery
    -0.58
    yip
    -0.56
     flares
    -0.56
    how
    -0.56
     textures
    -0.55
    POSITIVE LOGITS
     by
    0.88
     aback
    0.76
    uled
    0.73
     aboard
    0.71
    ô
    0.68
    DAQ
    0.68
    leep
    0.68
     alive
    0.67
     honorary
    0.67
    姫
    0.67
    Activations Density 0.140%

    No Known Activations