Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4521
    Prev
    Next
    INDEX
    Explanations

    statements of providing, publishing, directing, making, amending, registering, reproducing, amending, and presenting in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to the actions of providing, publishing, and directing materials or information

    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
    Shift
    -0.65
    tra
    -0.64
    Operation
    -0.61
    roots
    -0.60
    dor
    -0.59
     Blacks
    -0.59
    shift
    -0.58
    alon
    -0.57
     greens
    -0.56
     Sierra
    -0.56
    POSITIVE LOGITS
    ĸļ
    0.86
    inently
    0.81
     aback
    0.75
     proport
    0.75
    ependent
    0.74
    ertodd
    0.73
    ometimes
    0.72
     geographically
    0.72
    actionDate
    0.71
     herein
    0.69
    Activations Density 0.299%

    No Known Activations