© 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. 14759
    Prev
    Next
    INDEX
    Explanations

    the cause or motive behind events or actions

    oai_token-act-pair · gpt-3.5-turbo

    language related to motives and causes

    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
    abo
    -0.78
    owship
    -0.73
    gard
    -0.71
    buff
    -0.70
    udo
    -0.67
    NRS
    -0.65
    mun
    -0.65
    OWS
    -0.64
    paio
    -0.64
    byter
    -0.63
    POSITIVE LOGITS
     behind
    1.18
    why
    1.03
     motivating
    0.99
     underlying
    0.97
     motives
    0.95
     culprit
    0.95
     why
    0.92
     responsible
    0.92
     motive
    0.92
     motivations
    0.90
    Activations Density 0.273%

    No Known Activations