© 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. 11-RES-JB
    11. 12925
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussion and negotiation

    oai_token-act-pair · gpt-3.5-turbo

    negations and expressions of refusal or reluctance

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    senal
    -0.84
    etheless
    -0.76
    ãĥ¼ãĥĨ
    -0.71
    ¿½
    -0.69
     anecd
    -0.68
    antine
    -0.65
    mere
    -0.65
    moil
    -0.64
    undle
    -0.64
     largely
    -0.64
    POSITIVE LOGITS
    hin
    1.16
     wanna
    1.13
     ever
    0.97
     fuckin
    0.96
     fucking
    0.91
     breathe
    0.91
     belong
    0.90
    '."
    0.89
     deserve
    0.88
     EVEN
    0.88
    Activations Density 0.323%

    No Known Activations