© 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. 12-RES-JB
    11. 2417
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events or military figures

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    instances of the pronoun "he" and associated variations, indicating focus on male subjects or characters in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    PDATE
    -1.24
    senal
    -1.16
     practition
    -1.14
     millenn
    -1.13
    DAQ
    -1.11
    GoldMagikarp
    -1.06
    ĺħ
    -1.01
     antioxid
    -1.01
    Magikarp
    -1.01
     adolesc
    -0.98
    POSITIVE LOGITS
    'd
    1.29
     was
    1.16
     oversaw
    1.12
    aped
    1.08
     became
    1.04
     underwent
    1.04
     wasn
    1.03
     presided
    1.02
     withdrew
    1.02
     undertook
    1.02
    Activations Density 0.284%

    No Known Activations