© 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. 3-RES-JB
    11. 17177
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal documents or official statements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "affidavit."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    OPA
    -0.73
    rome
    -0.71
    ebus
    -0.69
     Nice
    -0.67
    âĹ¼
    -0.67
    enthal
    -0.66
    tan
    -0.66
    hoff
    -0.66
    obyl
    -0.64
    tics
    -0.64
    POSITIVE LOGITS
     affidavit
    1.09
    idav
    1.07
     affidav
    0.95
     synopsis
    0.85
     alleges
    0.83
     informant
    0.79
     conclud
    0.76
     recount
    0.75
     confession
    0.73
    endi
    0.72
    Activations Density 0.025%

    No Known Activations