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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 11343
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Cross" followed by other terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Cross" in various contexts, likely related to the "CrossFit" community or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.80
    ENCY
    -0.78
    acious
    -0.76
    ailable
    -0.75
     "$:/
    -0.70
     WATCHED
    -0.70
    OST
    -0.70
    ICAN
    -0.69
    URA
    -0.68
    ILY
    -0.68
    POSITIVE LOGITS
    roads
    1.37
    bones
    1.12
    Cross
    1.04
    cross
    1.03
    bow
    0.95
     Cross
    0.93
    bows
    0.89
    es
    0.87
    fax
    0.87
    hurst
    0.84
    Activations Density 0.007%

    No Known Activations