© 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. 1-RES-JB
    11. 20509
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with "Str" and followed by varying characters/types of names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Strang" and its variants in different contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ħĭ
    -0.79
    hyde
    -0.75
    choes
    -0.68
    ¥µ
    -0.68
    pie
    -0.67
    eals
    -0.66
    bear
    -0.66
    VERTIS
    -0.66
    eer
    -0.66
    vertis
    -0.65
    POSITIVE LOGITS
    icken
    0.96
     Str
    0.91
    atile
    0.89
    wcsstore
    0.88
    Str
    0.88
    angling
    0.85
    ategy
    0.81
    ategic
    0.80
    agh
    0.80
    ands
    0.78
    Activations Density 0.007%

    No Known Activations