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

    Neuronpedia

    Jacobian LensNEW
    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. 16612
    Prev
    Next
    INDEX
    Explanations

    phrases related to crossing or traversing from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "cross" and its variations related to movement or boundaries

    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
    rw
    -0.77
    rition
    -0.69
    liest
    -0.66
    nov
    -0.66
     rebate
    -0.62
    naissance
    -0.62
    eers
    -0.61
    za
    -0.61
    rike
    -0.61
    jury
    -0.61
    POSITIVE LOGITS
     paths
    1.26
     borders
    1.04
     boundaries
    0.93
     swords
    0.89
     jurisd
    0.89
     fences
    0.87
     continents
    0.87
     bridges
    0.84
     thresholds
    0.80
     bounds
    0.80
    Activations Density 0.063%

    No Known Activations