© 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. 18587
    Prev
    Next
    INDEX
    Explanations

    the term "cross" associated with various contexts such as "crossfire" or "cross-promotion."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cross" and its variations in different contexts

    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
    ICAN
    -0.73
    ulously
    -0.62
     McGee
    -0.62
     Learns
    -0.61
     Parenthood
    -0.60
     rall
    -0.60
     Ples
    -0.59
     Majority
    -0.59
    ECH
    -0.59
     Pione
    -0.58
    POSITIVE LOGITS
    roads
    1.61
    bow
    1.35
    hair
    1.27
    bows
    1.23
    word
    1.14
    bones
    1.13
    cutting
    1.12
    road
    1.05
    dress
    1.02
    cut
    0.98
    Activations Density 0.031%

    No Known Activations