© 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 EvalsExportsAPI 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. 9-RES-JB
    11. 5925
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific word, "Bal"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific entity or concept associated with "Bal."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä½ľ
    -0.70
    ä
    -0.69
     Patriot
    -0.69
     plural
    -0.67
    DAQ
    -0.64
     rpm
    -0.63
    æĸ¹
    -0.63
     Yankee
    -0.61
    LY
    -0.60
     Chaser
    -0.60
    POSITIVE LOGITS
    boa
    1.26
    ancing
    1.17
    oney
    1.06
    anca
    1.00
    zac
    1.00
    anced
    0.96
    aji
    0.94
    acl
    0.93
    inese
    0.92
    asar
    0.92
    Activations Density 0.026%

    No Known Activations