© 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. 8-RES-JB
    11. 12235
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations or landmarks

    oai_token-act-pair · gpt-3.5-turbo

    suffixes or word endings that indicate various parts of speech

    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
    ĨĴ
    -0.78
    GMT
    -0.67
    ģ«
    -0.64
    Termin
    -0.63
     irreversible
    -0.61
     euth
    -0.60
     commod
    -0.59
    Trend
    -0.59
    è¦ļéĨĴ
    -0.58
     casualty
    -0.57
    POSITIVE LOGITS
    inki
    0.81
    nen
    0.79
    puff
    0.78
    apa
    0.75
    oe
    0.74
    aun
    0.73
    urai
    0.73
    igans
    0.73
    ahs
    0.70
    ove
    0.70
    Activations Density 0.163%

    No Known Activations