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. 18133
    Prev
    Next
    INDEX
    Explanations

    terms related to electronics or technology

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Elect" in various contexts

    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
    ^^^^
    -0.79
    DERR
    -0.77
    OAD
    -0.73
    ========
    -0.73
    BuyableInstoreAndOnline
    -0.72
    acca
    -0.71
    REDACTED
    -0.69
    ciating
    -0.68
    *****
    -0.67
    WT
    -0.66
    POSITIVE LOGITS
    rification
    1.22
    ron
    1.12
    rics
    1.07
    elect
    1.06
    rons
    1.01
    ronic
    1.01
    rified
    1.00
    rum
    0.97
    rote
    0.97
    rical
    0.95
    Activations Density 0.008%

    No Known Activations