© 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. 8054
    Prev
    Next
    INDEX
    Explanations

    the word "casing" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the legal or regulatory context of cases

    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
    é¾įå
    -0.71
     Kardashian
    -0.70
     Europa
    -0.65
     Mercury
    -0.65
    LEASE
    -0.65
     unm
    -0.65
     Naked
    -0.64
     Happiness
    -0.61
     Penguin
    -0.61
     handshake
    -0.59
    POSITIVE LOGITS
     cas
    1.23
    hews
    1.03
    hew
    1.00
    ques
    0.97
    grain
    0.91
    imir
    0.88
    ificial
    0.87
     caster
    0.85
    bah
    0.84
    opher
    0.84
    Activations Density 0.005%

    No Known Activations