© 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. 9-RES-JB
    11. 24203
    Prev
    Next
    INDEX
    Explanations

    political statements introduced by the word "as"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "as" used to introduce comparisons or explanations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    +.
    -0.71
    SourceFile
    -0.65
    iard
    -0.63
    taboola
    -0.63
     marrow
    -0.62
    AAAAAAAA
    -0.61
    =-=-
    -0.59
    >:
    -0.59
    stice
    -0.59
     IDs
    -0.58
    POSITIVE LOGITS
     happened
    0.87
     advocated
    0.83
     usual
    0.81
     happens
    0.76
     occurred
    0.76
     hoped
    0.74
     transpired
    0.74
    lihood
    0.72
     proponents
    0.72
     critics
    0.72
    Activations Density 0.200%

    No Known Activations