© 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. 3-RES-JB
    11. 4376
    Prev
    Next
    INDEX
    Explanations

    mentions of successful achievements or accomplishments, particularly in sports contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "finished" and its variations, indicating completion or conclusion in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tan
    -0.87
    learn
    -0.83
    Lear
    -0.81
    orb
    -0.80
    arin
    -0.79
    ships
    -0.76
    tar
    -0.76
    eye
    -0.74
    Enlarge
    -0.72
    moon
    -0.72
    POSITIVE LOGITS
     finish
    0.75
     unbeaten
    0.75
     undefeated
    0.74
    nces
    0.73
    ãĤ¤ãĥĪ
    0.71
     runner
    0.70
     finishing
    0.70
     stuffing
    0.69
     eighth
    0.68
     ninth
    0.67
    Activations Density 0.013%

    No Known Activations