© 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. 14774
    Prev
    Next
    INDEX
    Explanations

    names preceded by a possessive ('s)

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms referring to individuals or entities

    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
    olkien
    -0.89
    Developer
    -0.87
    ISO
    -0.76
    selves
    -0.76
    hari
    -0.74
    lishes
    -0.73
    lehem
    -0.73
    unin
    -0.73
    anguage
    -0.72
    TAIN
    -0.71
    POSITIVE LOGITS
     birthplace
    0.96
     departure
    0.93
     penchant
    0.93
     signature
    0.92
     whereabouts
    0.91
     birthday
    0.91
     own
    0.91
     hometown
    0.90
     widow
    0.89
     insistence
    0.88
    Activations Density 0.142%

    No Known Activations