© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 13121
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to perception or opinion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "see" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     whistle
    -0.69
    nesia
    -0.63
     withd
    -0.61
     suspense
    -0.58
     agric
    -0.58
    Tweet
    -0.57
    eware
    -0.57
    mort
    -0.56
    cious
    -0.55
     ILCS
    -0.54
    POSITIVE LOGITS
     parallels
    1.01
     fit
    1.00
    awed
    0.92
    dust
    0.91
     visions
    0.87
    Ĺ
    0.85
     eye
    0.84
    enance
    0.80
     similarities
    0.77
    WARD
    0.76
    Activations Density 0.085%

    No Known Activations