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. 3-RES-JB
    6. 7784
    Prev
    Next
    INDEX
    Explanations

    words related to specific proper nouns or terms which start with 'Occ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Occasional" and its variations, and also terms related to the concept of re-emergence or resurrection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HCR
    -0.86
    BuyableInstoreAndOnline
    -0.78
    BIL
    -0.74
    shapeshifter
    -0.73
    NESS
    -0.73
    RAW
    -0.70
     Gork
    -0.69
    DI
    -0.68
    SIZE
    -0.68
    ERAL
    -0.65
    POSITIVE LOGITS
    idental
    1.03
    urrence
    1.00
    occ
    0.97
    urred
    0.97
    uria
    0.94
    urs
    0.93
    urring
    0.87
     occ
    0.85
    asions
    0.84
    asionally
    0.83
    Activations Density 0.006%

    No Known Activations