© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 23394
    Prev
    Next
    INDEX
    Explanations

    phrases related to explanations or clarifications

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "explained" and its variations, particularly in contexts of clarification or elaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.79
    brance
    -0.75
    soever
    -0.72
    ene
    -0.72
    definition
    -0.70
    otin
    -0.66
    tery
    -0.63
    iac
    -0.63
    illions
    -0.63
    abases
    -0.62
    POSITIVE LOGITS
     bluntly
    0.83
     afterwards
    0.82
    WER
    0.79
     sarcast
    0.77
    :"
    0.77
     that
    0.76
     afterward
    0.75
     why
    0.69
     emphatically
    0.68
     how
    0.68
    Activations Density 0.195%

    No Known Activations