© 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. 2-RES-JB
    11. 18397
    Prev
    Next
    INDEX
    Explanations

    words relating to authenticity or reality

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "real" 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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    xual
    -0.82
    ebook
    -0.77
    berries
    -0.70
     Carbuncle
    -0.68
    awk
    -0.68
    asers
    -0.66
    549
    -0.65
     Presbyter
    -0.64
    heid
    -0.63
    MENTS
    -0.63
    POSITIVE LOGITS
    ignment
    1.37
     estate
    1.18
    igning
    1.16
    isation
    1.13
    igned
    1.11
    polit
    1.08
    isable
    1.00
    DonaldTrump
    0.95
    izations
    0.95
    istic
    0.95
    Activations Density 0.027%

    No Known Activations