© 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. 6-RES-JB
    11. 966
    Prev
    Next
    INDEX
    Explanations

    the word "in" followed by a specific country or city name

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "ia"

    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
     glim
    -0.78
    inances
    -0.77
    alogue
    -0.76
    alore
    -0.73
    mans
    -0.70
    IFIED
    -0.69
    iaries
    -0.66
    straight
    -0.65
    wcsstore
    -0.65
    ainted
    -0.65
    POSITIVE LOGITS
    zza
    1.32
    ppe
    1.19
    BILITY
    1.04
     nerv
    1.00
    pered
    0.99
    ppa
    0.98
    ffe
    0.98
    ccess
    0.97
    ÅĤ
    0.96
     coli
    0.94
    Activations Density 0.034%

    No Known Activations