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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11482
    Prev
    Next
    INDEX
    Explanations

    the word "visibility' in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "vis" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sharp
    -0.72
    CDC
    -0.70
    payment
    -0.67
    ago
    -0.67
     AJ
    -0.66
    Christmas
    -0.66
     Grove
    -0.65
     Andromeda
    -0.65
     Northwest
    -0.65
    idays
    -0.63
    POSITIVE LOGITS
     vis
    4.09
     viz
    1.47
     visc
    1.20
    externalActionCode
    1.19
     VIS
    1.10
    vis
    1.03
     Vis
    0.97
     dur
    0.96
     territ
    0.96
     reflective
    0.94
    Activations Density 0.023%

    No Known Activations