© 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. 10-RES-JB
    11. 7791
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a decision or responsibility assigned to someone

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "up to," suggesting a focus on responsibility or decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VICE
    -0.60
     Flavoring
    -0.59
     understatement
    -0.59
    thia
    -0.58
     diseng
    -0.55
    Untitled
    -0.55
    aves
    -0.54
     Frag
    -0.54
     Liter
    -0.54
    isha
    -0.52
    POSITIVE LOGITS
    ended
    1.03
    vote
    0.91
    regulated
    0.91
    votes
    0.90
    swing
    0.89
    bra
    0.89
    sell
    0.88
    graded
    0.87
    rated
    0.87
    stairs
    0.86
    Activations Density 0.038%

    No Known Activations