© 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. 17322
    Prev
    Next
    INDEX
    Explanations

    dates related to historical events, specifically focusing on September 11th

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific dates, particularly in September

    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
     hepat
    -0.66
    shr
    -0.64
    ying
    -0.62
    kus
    -0.61
    Interstitial
    -0.61
    transform
    -0.60
     bleach
    -0.60
    shake
    -0.59
    UGH
    -0.59
    jri
    -0.59
    POSITIVE LOGITS
     2018
    0.92
     29
    0.88
     Ago
    0.86
     27
    0.85
     11
    0.85
    eteenth
    0.83
     1862
    0.82
     26
    0.82
     28
    0.80
     2013
    0.80
    Activations Density 0.022%

    No Known Activations