© 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. 8788
    Prev
    Next
    INDEX
    Explanations

    legal or regulatory implications and requirements, particularly related to forms or legal actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases and clauses that reference legal or regulatory contexts

    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
    itialized
    -0.82
    erest
    -0.81
    eco
    -0.77
    uther
    -0.73
    )</
    -0.71
     brill
    -0.71
    vae
    -0.70
    joy
    -0.67
    rir
    -0.67
    ÑĤ
    -0.65
    POSITIVE LOGITS
     according
    1.12
     regardless
    0.99
     thereby
    0.92
     POLITICO
    0.91
     meaning
    0.90
     irrespective
    0.88
     whichever
    0.88
    according
    0.80
     respectively
    0.80
     spokeswoman
    0.79
    Activations Density 0.312%

    No Known Activations