© 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. 7-RES-JB
    11. 1811
    Prev
    Next
    INDEX
    Explanations

    words containing the suffix "-ing"

    oai_token-act-pair · gpt-3.5-turbo

    words ending in "ing" or "ed"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seat
    -0.90
     Corinth
    -0.65
     seat
    -0.63
     Companion
    -0.63
     Pric
    -0.63
    ttes
    -0.61
     EPS
    -0.61
     substitutes
    -0.61
     Buddy
    -0.61
     parap
    -0.60
    POSITIVE LOGITS
    redients
    0.86
    iannopoulos
    0.83
    verage
    0.82
    ertain
    0.81
    mination
    0.80
    bert
    0.79
    jac
    0.79
    lass
    0.78
    clair
    0.77
    oj
    0.76
    Activations Density 0.027%

    No Known Activations