© 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. 7-RES-JB
    11. 1722
    Prev
    Next
    INDEX
    Explanations

    instances of the preposition "in" followed by other words

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the phrase "in" followed by contextually relevant information

    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
    bos
    -0.74
    irl
    -0.71
    LOG
    -0.70
    BIL
    -0.70
    hester
    -0.69
    Attempts
    -0.68
    hov
    -0.68
    ENCE
    -0.68
    alion
    -0.66
    gans
    -0.66
    POSITIVE LOGITS
    clusions
    1.19
    animate
    1.09
    versions
    1.04
     lieu
    0.99
     relation
    0.96
    between
    0.95
    organic
    0.94
    appropriate
    0.94
    effic
    0.93
     totality
    0.91
    Activations Density 0.351%

    No Known Activations