© 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. 9-RES-JB
    11. 17370
    Prev
    Next
    INDEX
    Explanations

    phrases related to praising or highlighting positive aspects or qualities

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating attributes or characteristics of various subjects

    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
    ussia
    -0.64
    ocaust
    -0.63
    answered
    -0.62
    figure
    -0.62
    eve
    -0.61
    usk
    -0.61
    姫
    -0.61
    akh
    -0.60
     Pension
    -0.60
     Beir
    -0.59
    POSITIVE LOGITS
     its
    0.94
     versatility
    0.90
     simplicity
    0.89
     unpredict
    0.78
     flexibility
    0.78
     resemblance
    0.76
     cumbers
    0.75
     susceptibility
    0.74
     uniqueness
    0.73
     unmatched
    0.72
    Activations Density 0.376%

    No Known Activations