© 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. 13823
    Prev
    Next
    INDEX
    Explanations

    adverbs describing a significant change or impact

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant changes in values or metrics

    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
     absolutely
    -0.65
    ilater
    -0.59
    ilan
    -0.58
     downright
    -0.58
    byter
    -0.58
    pron
    -0.58
    ãĥ¯ãĥ³
    -0.58
     totally
    -0.57
     supreme
    -0.57
    oute
    -0.55
    POSITIVE LOGITS
     thereafter
    0.80
     toward
    0.78
     during
    0.78
     towards
    0.75
     afterward
    0.73
     afterwards
    0.70
     (>
    0.68
     enough
    0.67
     throughout
    0.67
     into
    0.66
    Activations Density 0.123%

    No Known Activations