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. 4-RES-JB
    6. 5979
    Prev
    Next
    INDEX
    Explanations

    mentions of the IDF (Israel Defense Forces)

    oai_token-act-pair · gpt-3.5-turbo

    references to the IDF and TTC organizations

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

    No Comments

    Negative Logits
    phal
    -0.78
    views
    -0.71
    felt
    -0.70
    luaj
    -0.69
    Joy
    -0.68
    rors
    -0.68
    porting
    -0.68
    fried
    -0.66
    itarian
    -0.66
    rencies
    -0.65
    POSITIVE LOGITS
    CCC
    0.95
    VICE
    0.83
    PA
    0.82
    ANY
    0.80
    ESH
    0.80
    DF
    0.78
    WD
    0.78
    REP
    0.78
    ACY
    0.77
    ENTION
    0.77
    Activations Density 0.016%

    No Known Activations