© 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. 8-RES-JB
    11. 10524
    Prev
    Next
    INDEX
    Explanations

    superlatives or highest degrees of comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express extreme opinions or experiences related to seeing or hearing something

    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
    pron
    -0.66
    Newsletter
    -0.64
    Morning
    -0.64
    laws
    -0.64
    mber
    -0.63
    isites
    -0.63
    Introduced
    -0.62
    later
    -0.60
     occasional
    -0.59
    2015
    -0.59
    POSITIVE LOGITS
    !.
    0.78
    Merit
    0.73
    >]
    0.73
    !:
    0.73
     anywhere
    0.73
    .}
    0.72
    !".
    0.72
    !",
    0.72
    !,
    0.68
     mankind
    0.68
    Activations Density 0.193%

    No Known Activations