© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 2414
    Prev
    Next
    INDEX
    Explanations

    quotes or excerpts from philosophical discussions

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

    instances of advertisement content

    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
     Leilan
    -0.90
    ãĤ¢ãĥ«
    -0.85
     eviction
    -0.74
    ãĥ´
    -0.72
    628
    -0.69
    866
    -0.69
    SEA
    -0.68
    sel
    -0.65
     Takeru
    -0.65
    activ
    -0.64
    POSITIVE LOGITS
    BIT
    0.96
    bit
    0.86
     Bit
    0.82
     Thanks
    0.81
     Credit
    0.77
     thank
    0.77
     thanks
    0.76
    thanks
    0.75
     BIT
    0.75
    Bit
    0.75
    Activations Density 0.140%

    No Known Activations