© 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. 23965
    Prev
    Next
    INDEX
    Explanations

    phrases related to political representatives

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "representative" or references to political representatives

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.84
    glers
    -0.75
     factor
    -0.73
    phal
    -0.72
     underpin
    -0.69
    istically
    -0.68
     Dwar
    -0.64
     factors
    -0.63
     bul
    -0.61
     blight
    -0.60
    POSITIVE LOGITS
    orters
    1.40
    orter
    1.35
    utation
    1.23
    ublic
    1.20
    rint
    1.18
    orted
    1.16
    atri
    1.15
    airs
    1.14
    ository
    1.13
    rieve
    1.09
    Activations Density 0.025%

    No Known Activations