© 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. 12-RES-JB
    11. 5087
    Prev
    Next
    INDEX
    Explanations

    phrases related to recommendations

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    strong recommendations or endorsements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    idable
    -0.64
    actly
    -0.59
    oths
    -0.56
    yz
    -0.56
    ither
    -0.56
     neatly
    -0.56
     brilliantly
    -0.55
     Strike
    -0.55
    MAT
    -0.54
    neath
    -0.53
    POSITIVE LOGITS
     recommend
    1.20
     encourage
    1.10
     suggest
    0.98
     advise
    0.97
     Recommend
    0.95
     appre
    0.94
     discourage
    0.93
     recomm
    0.92
     recommends
    0.91
     encour
    0.89
    Activations Density 0.065%

    No Known Activations