© 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. 2-RES-JB
    11. 6795
    Prev
    Next
    INDEX
    Explanations

    numbers with a specific pattern, particularly the sequence "800" followed by another digit

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with the number 800

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uked
    -0.77
    lict
    -0.75
    ributed
    -0.74
    agn
    -0.73
    bid
    -0.72
    unal
    -0.71
     shepherd
    -0.70
     symmetry
    -0.70
    oral
    -0.69
    inance
    -0.69
    POSITIVE LOGITS
    800
    0.94
     MHz
    0.88
    989
    0.86
    700
    0.83
    Hz
    0.82
    600
    0.81
    ãĥ¼ãĥĨãĤ£
    0.80
    400
    0.78
    000
    0.77
     msec
    0.75
    Activations Density 0.016%

    No Known Activations