© 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. 0-RES-JB
    11. 2602
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "occurrence" or its variations in the text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "occurrence"

    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
     Shot
    -0.81
     Reboot
    -0.76
     proof
    -0.67
     depreciation
    -0.63
     racks
    -0.59
     pledged
    -0.58
     Ammunition
    -0.58
    dash
    -0.58
    mad
    -0.58
    Sword
    -0.57
    POSITIVE LOGITS
    occ
    4.60
    Occ
    2.50
     Occ
    2.23
     occ
    2.13
     occurrence
    1.62
     occurrences
    1.22
     occurring
    1.17
     happ
    1.10
     occur
    1.10
    exist
    1.06
    Activations Density 0.017%

    No Known Activations