© 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. 2-RES-JB
    11. 9010
    Prev
    Next
    INDEX
    Explanations

    capitalized words starting with "Ar" followed by numeric values or names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Ar" followed by numbers or related names

    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
    assetsadobe
    -0.78
    ¬¼
    -0.74
    iculty
    -0.74
    ĸļ
    -0.72
    stakes
    -0.72
    姫
    -0.69
    å¸
    -0.67
    eners
    -0.66
    sylvania
    -0.66
    æĸ¹
    -0.66
    POSITIVE LOGITS
    ithmetic
    0.99
    issa
    0.96
    thritis
    0.94
    beit
    0.92
    ign
    0.91
    ranging
    0.89
    leigh
    0.88
    izoph
    0.88
    ansas
    0.85
    ranged
    0.85
    Activations Density 0.009%

    No Known Activations