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. 23745
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "separation."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of separation, particularly in relation to church and state

    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
    cycl
    -0.66
    nz
    -0.65
    WN
    -0.64
    rouse
    -0.64
    vous
    -0.63
    OD
    -0.63
    mA
    -0.62
    jury
    -0.62
    ×Ķ
    -0.62
    herty
    -0.62
    POSITIVE LOGITS
     separating
    0.92
    separ
    0.91
     separ
    0.88
     separated
    0.86
     separation
    0.80
    imore
    0.77
    inguished
    0.76
    aration
    0.76
     sexes
    0.76
    ĨĴ
    0.75
    Activations Density 0.025%

    No Known Activations