Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 21920
    Prev
    Next
    INDEX
    Explanations

    dates or numbers in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the date "Mar 9" and similar date formats

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

    No Comments

    Negative Logits
    éĹĺ
    -1.06
    ħĭ
    -0.96
    anwhile
    -0.86
    é¾įå¥ij士
    -0.82
     tray
    -0.76
    ngth
    -0.76
    ij士
    -0.73
    uyomi
    -0.70
    âĶģ
    -0.69
     Regulatory
    -0.69
    POSITIVE LOGITS
    riages
    1.08
    ital
    1.03
    ried
    1.01
    riage
    1.00
    azz
    0.99
    aqu
    0.96
    lene
    0.95
    ice
    0.93
    iscal
    0.90
    isco
    0.88
    Activations Density 0.013%

    No Known Activations