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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 9900
    Prev
    Next
    INDEX
    Explanations

    years mentioned in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years or chronological events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Otherwise
    -0.73
    arah
    -0.72
    apest
    -0.68
    ãĥ¥
    -0.68
    ãĤ¦ãĤ¹
    -0.68
    ãĤ§
    -0.67
    ////////////////
    -0.67
    ãĤ´ãĥ³
    -0.63
    ]);
    -0.62
    alogy
    -0.61
    POSITIVE LOGITS
     however
    0.90
     when
    0.86
    when
    0.82
     shortly
    0.82
     Newsweek
    0.81
     Forbes
    0.78
    upon
    0.77
     amid
    0.77
     while
    0.75
     according
    0.71
    Activations Density 0.165%

    No Known Activations