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. 9-RES-JB
    6. 604
    Prev
    Next
    INDEX
    Explanations

    words related to Serbian culture or history

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Ser" followed by the number 3

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ELS
    -0.71
    ORN
    -0.70
    enegger
    -0.66
    è£ħ
    -0.64
    EEK
    -0.64
    DERR
    -0.63
     Beckham
    -0.62
    OWS
    -0.62
     SOS
    -0.61
    ESCO
    -0.60
    POSITIVE LOGITS
    geant
    1.32
    otonin
    1.16
    rano
    1.14
    pent
    1.12
    ials
    1.03
    mons
    0.92
    gue
    0.90
    gent
    0.88
    bian
    0.87
    igraph
    0.86
    Activations Density 0.039%

    No Known Activations