© 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. 8-RES-JB
    11. 2447
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name, "Ali"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the substring "ali" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acters
    -0.84
    theless
    -0.83
    inately
    -0.80
    ried
    -0.78
    ilaterally
    -0.74
    stairs
    -0.73
    ancial
    -0.73
    ifiable
    -0.71
    mil
    -0.71
    meyer
    -0.71
    POSITIVE LOGITS
    Äĩ
    1.14
    yah
    1.05
    ño
    1.03
    ñ
    1.03
    ya
    0.97
    ña
    0.96
    á¹
    0.86
    qt
    0.84
     versa
    0.82
    Äį
    0.82
    Activations Density 0.094%

    No Known Activations