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

    Neuronpedia

    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. 7-RES-JB
    11. 1576
    Prev
    Next
    INDEX
    Explanations

    dates and months in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates or years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tumblr
    -0.95
    ï¸ı
    -0.78
    earable
    -0.78
     ponds
    -0.76
    urgy
    -0.71
    usercontent
    -0.71
    ngth
    -0.70
    edience
    -0.67
    estern
    -0.66
    raq
    -0.65
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.80
     Centauri
    0.67
     ç¥ŀ
    0.64
     Vera
    0.60
    araoh
    0.60
    ãĤ·ãĥ£
    0.57
    umbing
    0.57
     governors
    0.56
     Dealer
    0.56
     bye
    0.54
    Activations Density 0.232%

    No Known Activations