© 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. 9-RES-JB
    11. 23212
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and controversies

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating areas or topics of restriction or connection

    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
     decay
    -0.57
    rament
    -0.55
     KL
    -0.55
    kan
    -0.53
    inguishable
    -0.51
    redo
    -0.51
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.49
     Whit
    -0.48
     vet
    -0.48
     Comparison
    -0.48
    POSITIVE LOGITS
    ascript
    0.92
     thereto
    0.89
    dayName
    0.75
    hart
    0.74
    oldown
    0.71
    hran
    0.67
    berus
    0.64
    ãĤ´ãĥ³
    0.64
    verage
    0.63
     to
    0.62
    Activations Density 0.428%

    No Known Activations