© 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. 1-RES-JB
    11. 9449
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to crossover events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "crossover" and related concepts indicating connections or intersections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oran
    -0.71
    orius
    -0.71
    yre
    -0.70
    ogy
    -0.65
    orio
    -0.65
    Ķ
    -0.65
     Lav
    -0.64
    OST
    -0.63
    enance
    -0.62
    bis
    -0.62
    POSITIVE LOGITS
     crossover
    1.46
    rossover
    1.46
    rosso
    1.11
     shenan
    0.89
    halla
    0.76
    iflower
    0.74
    theless
    0.74
    atform
    0.73
    wake
    0.72
    istani
    0.67
    Activations Density 0.005%

    No Known Activations