© 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. 2-RES-JB
    11. 8284
    Prev
    Next
    INDEX
    Explanations

    instances of the word "crossed"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.84
    andum
    -0.80
    idity
    -0.76
    姫
    -0.75
    abilia
    -0.74
    ccording
    -0.68
    ately
    -0.66
    VERTISEMENT
    -0.66
    cknowled
    -0.66
     Tycoon
    -0.65
    POSITIVE LOGITS
     crossing
    0.94
     crossings
    0.91
     crossed
    0.91
    roads
    0.89
     crosses
    0.81
    bones
    0.79
     paths
    0.78
    agues
    0.76
     swords
    0.74
    cross
    0.73
    Activations Density 0.008%

    No Known Activations