© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 2267
    Prev
    Next
    INDEX
    Explanations

    words related to electricity or electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "elect" or its variations, which are related to elections or electrical concepts

    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
    Lens
    -0.74
    ĸļ
    -0.71
     Flavoring
    -0.70
    acca
    -0.67
    ACK
    -0.65
    xus
    -0.65
    OAD
    -0.65
    ^^^^
    -0.64
    ========
    -0.64
    BuyableInstoreAndOnline
    -0.63
    POSITIVE LOGITS
    ron
    1.17
    rification
    1.12
    rified
    1.09
    rons
    1.09
    roc
    1.07
    rated
    1.03
    eering
    1.01
    rum
    1.00
    rics
    0.99
    rote
    0.97
    Activations Density 0.011%

    No Known Activations