© 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. 10-RES-JB
    11. 11378
    Prev
    Next
    INDEX
    Explanations

    the word "impression" or "perception."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concepts of impression and perception

    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
    sil
    -0.69
    ratulations
    -0.67
    vertisement
    -0.67
    eni
    -0.64
    talking
    -0.64
    enhagen
    -0.63
    ingen
    -0.62
    loads
    -0.61
    asms
    -0.60
     dismant
    -0.60
    POSITIVE LOGITS
     impression
    0.80
    istic
    0.80
     Lauder
    0.79
     perceptions
    0.76
    ally
    0.76
     perception
    0.73
    wcsstore
    0.73
     impaired
    0.71
     biases
    0.69
     impressions
    0.69
    Activations Density 0.056%

    No Known Activations