© 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. 20744
    Prev
    Next
    INDEX
    Explanations

    items or locations in a setting such as a kiosk, a shoe-shine stand, a stop, or a studio

    oai_token-act-pair · gpt-3.5-turbo

    references to specific commercial or service establishments

    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
    enhagen
    -0.70
    wal
    -0.60
    ivas
    -0.58
    otine
    -0.56
    Lower
    -0.54
     Villa
    -0.54
    lower
    -0.53
    wei
    -0.53
     Coco
    -0.53
     Sever
    -0.53
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.72
    dayName
    0.71
    ĵĺ
    0.66
    ikini
    0.62
     lett
    0.62
     Hatch
    0.60
    aware
    0.59
    çĶ°
    0.59
     Khan
    0.58
     quake
    0.58
    Activations Density 1.105%

    No Known Activations