© 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. 7-RES-JB
    11. 23498
    Prev
    Next
    INDEX
    Explanations

    phrases related to movements or actions alternating between two entities or locations

    oai_token-act-pair · gpt-3.5-turbo

    the repetitive phrase "back and forth."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ZA
    -0.81
    merce
    -0.68
    GD
    -0.63
    lio
    -0.61
    icity
    -0.61
    scribe
    -0.60
    mental
    -0.60
    LI
    -0.59
    âĦ¢:
    -0.59
    ogens
    -0.59
    POSITIVE LOGITS
     forth
    1.21
    alus
    0.80
     Forth
    0.79
    forth
    0.76
    romeda
    0.72
     vice
    0.68
     whence
    0.64
    aunder
    0.62
     Reilly
    0.60
     throats
    0.59
    Activations Density 0.070%

    No Known Activations