© 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. 19572
    Prev
    Next
    INDEX
    Explanations

    terms related to advertisements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of advertisements

    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
    20439
    -0.85
    ĨĴ
    -0.82
    Jr
    -0.74
    displayText
    -0.71
    bred
    -0.70
     Cyprus
    -0.69
    ppa
    -0.67
     Carbuncle
    -0.66
    quartered
    -0.63
    prototype
    -0.63
    POSITIVE LOGITS
    vertising
    1.14
    verts
    1.10
    strip
    0.99
    orial
    0.98
     hoard
    0.94
    elaide
    0.92
    vertisement
    0.90
    vertis
    0.86
    roit
    0.86
     nause
    0.85
    Activations Density 0.049%

    No Known Activations