© 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. 4967
    Prev
    Next
    INDEX
    Explanations

    keywords related to personal experiences or reflections

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

    references to personal and emotional experiences

    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
     Adds
    -1.14
    senal
    -1.13
    emale
    -1.07
    %:
    -1.05
    ortunately
    -0.98
    eatures
    -0.97
    ouble
    -0.93
     Parables
    -0.92
    CRIP
    -0.91
    osures
    -0.91
    POSITIVE LOGITS
     was
    1.24
     resembled
    1.11
     wore
    1.10
     bore
    1.09
     wasn
    1.05
     lacked
    1.05
     belonged
    1.04
     existed
    1.02
     seemed
    1.01
     grew
    1.01
    Activations Density 0.684%

    No Known Activations