© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 3636
    Prev
    Next
    INDEX
    Explanations

    words related to pomegranate

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ome."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pring
    -0.78
    Ó
    -0.70
    iversal
    -0.68
    ariat
    -0.66
    olicy
    -0.65
    ive
    -0.65
    hops
    -0.65
    lished
    -0.64
    icter
    -0.64
    idious
    -0.64
    POSITIVE LOGITS
    gran
    1.00
    ome
    0.89
    chan
    0.83
    lda
    0.77
    ña
    0.77
    lette
    0.76
    ppa
    0.75
    gger
    0.75
    gon
    0.73
    cles
    0.70
    Activations Density 0.028%

    No Known Activations