© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11604
    Prev
    Next
    INDEX
    Explanations

    terms related to counting or quantifying specific items or attributes

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data and counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffffcc
    -0.89
    ãĤ´ãĥ³
    -0.88
    çīĪ
    -0.78
     guise
    -0.74
     sensibilities
    -0.74
    lace
    -0.70
     srfAttach
    -0.67
    tainment
    -0.64
    haven
    -0.63
     opio
    -0.63
    POSITIVE LOGITS
     per
    1.04
     counted
    1.02
     consumed
    0.95
     available
    0.93
     attributable
    0.92
     devoted
    0.90
     allowable
    0.90
     needed
    0.88
     required
    0.88
     permissible
    0.86
    Activations Density 0.270%

    No Known Activations