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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16463
    Prev
    Next
    INDEX
    Explanations

    words related to places or settings, particularly emphasizing specific characteristics within a place

    oai_token-act-pair · gpt-3.5-turbo

    nouns and terms related to specific places and legal or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rencies
    -0.82
    assies
    -0.82
    urches
    -0.80
    doms
    -0.76
    nces
    -0.73
    events
    -0.73
    lees
    -0.73
     Machines
    -0.72
     Scenes
    -0.72
    urrencies
    -0.70
    POSITIVE LOGITS
     standpoint
    0.89
     contender
    0.69
     variant
    0.68
     sized
    0.68
     piece
    0.67
    oser
    0.66
     perspective
    0.66
     apiece
    0.65
    ogram
    0.65
     basis
    0.64
    Activations Density 1.784%

    No Known Activations