© 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. 6-RES-JB
    11. 9655
    Prev
    Next
    INDEX
    Explanations

    words or parts of words related to numbers, especially with the suffixes "-teen" or "-ty"

    oai_token-act-pair · gpt-3.5-turbo

    words and suffixes related to the concept of "twenty."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inaction
    -0.75
    ONSORED
    -0.73
    ansas
    -0.71
     lapse
    -0.70
     environment
    -0.69
     Admission
    -0.69
     admission
    -0.67
     congestion
    -0.66
     neglect
    -0.66
     ignorance
    -0.65
    POSITIVE LOGITS
    lang
    0.85
    kered
    0.77
    oots
    0.75
    Pic
    0.74
    ieth
    0.73
    puff
    0.73
    lde
    0.72
    irds
    0.71
    ipe
    0.71
    upon
    0.69
    Activations Density 0.093%

    No Known Activations