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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 259
    Prev
    Next
    INDEX
    Explanations

    words that start with the letters "occ"

    oai_token-act-pair · gpt-4-turbo

    references to specific institutions and terms related to academia

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Occ" or variations of it related to events or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shapeshifter
    -0.77
    BIL
    -0.77
    HCR
    -0.77
    RAW
    -0.74
     TED
    -0.72
    åĤ
    -0.70
    DI
    -0.69
    dash
    -0.68
    externalActionCode
    -0.65
    EMENT
    -0.64
    POSITIVE LOGITS
    occ
    1.09
    asionally
    1.01
    urred
    1.00
    idental
    0.96
    urrence
    0.90
    urring
    0.90
    ŃĶ
    0.89
     occ
    0.89
    asions
    0.87
    uria
    0.86
    Activations Density 0.005%

    No Known Activations