© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9590
    Prev
    Next
    INDEX
    Explanations

    words containing the sequence "wr"

    oai_token-act-pair · gpt-3.5-turbo
    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
    ãĥ´
    -0.68
    RON
    -0.66
     Defenders
    -0.60
     [|
    -0.59
    croft
    -0.59
     Earth
    -0.59
     Manifest
    -0.58
    schild
    -0.58
     Pixie
    -0.57
     AMERICA
    -0.57
    POSITIVE LOGITS
    inkle
    1.34
    ights
    1.30
    angling
    1.14
    ight
    1.14
    angler
    1.11
    angled
    1.10
    acked
    1.05
    itting
    1.05
    angle
    1.04
    acking
    1.01
    Activations Density 0.039%

    No Known Activations