© 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. 16005
    Prev
    Next
    INDEX
    Explanations

    proper nouns or phrases possibly related to places or people, particularly those with the name "Ia."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ia" in various contexts

    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
     ancest
    -0.73
    soDeliveryDate
    -0.73
    acles
    -0.72
    alore
    -0.70
    wcsstore
    -0.69
     glim
    -0.67
    OWER
    -0.66
    emporary
    -0.65
    lined
    -0.64
     citiz
    -0.64
    POSITIVE LOGITS
    zza
    1.24
    ppe
    1.24
     nerv
    1.02
    BILITY
    1.01
    ppa
    0.99
    pered
    0.98
    ccess
    0.93
    ulia
    0.91
    ea
    0.89
    lda
    0.89
    Activations Density 0.019%

    No Known Activations