Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 8-RES-JB
    6. 6672
    Prev
    Next
    INDEX
    Explanations

    phrases containing the text "Fe" followed by a single digit between 8 and 10

    oai_token-act-pair · gpt-3.5-turbo

    references to the character or person "Fe."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Columbia
    -0.74
     Nadu
    -0.68
    OWER
    -0.67
    ABLE
    -0.66
    =-=-=-=-=-=-=-=-
    -0.64
     guiActiveUnfocused
    -0.64
    aneously
    -0.64
     STATES
    -0.62
    icious
    -0.61
    565
    -0.61
    POSITIVE LOGITS
    plin
    1.12
    clair
    1.03
    ifax
    0.98
    uth
    0.95
    alty
    0.94
    ulner
    0.94
    acebook
    0.93
    kens
    0.88
    imar
    0.88
    vern
    0.87
    Activations Density 0.046%

    No Known Activations