© 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. 12613
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Malawi" or words related to it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "m" and its associated combinations in various contexts

    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
     explan
    -0.67
    :{
    -0.60
     facult
    -0.59
     acron
    -0.58
    iliary
    -0.57
     dunno
    -0.57
    glers
    -0.57
    itiveness
    -0.56
     inactive
    -0.56
     ok
    -0.56
    POSITIVE LOGITS
    nikov
    0.87
    esi
    0.86
    Ń·
    0.85
    mson
    0.84
    agne
    0.79
    ieri
    0.79
    hemy
    0.76
    ãĤ¶
    0.76
    ioxide
    0.76
    aughs
    0.75
    Activations Density 0.099%

    No Known Activations