© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 22532
    Prev
    Next
    INDEX
    Explanations

    significant events or achievements

    oai_token-act-pair · gpt-3.5-turbo

    references to significant achievements or markers of progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.91
    otto
    -0.81
    obar
    -0.77
    obe
    -0.76
    ately
    -0.74
    oks
    -0.72
    amina
    -0.70
    ²¾
    -0.69
    opoly
    -0.69
    piracy
    -0.69
    POSITIVE LOGITS
     milestone
    1.26
     milestones
    1.23
     celebrations
    0.81
     achievement
    0.78
     hurdle
    0.75
    catentry
    0.74
     achievements
    0.73
    posts
    0.73
     hurdles
    0.73
     anniversary
    0.70
    Activations Density 0.009%

    No Known Activations