© 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. 6-RES-JB
    11. 2994
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    instances of certain capitalized words or phrases, particularly those starting with "Sp"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĥĪ
    -0.83
    ĸļ
    -0.77
    ĪĴ
    -0.73
    İĭ
    -0.70
    hof
    -0.69
    âĸ¬âĸ¬
    -0.68
     STATES
    -0.66
    WAYS
    -0.65
     separatist
    -0.65
    vironment
    -0.65
    POSITIVE LOGITS
    atial
    1.22
    ooky
    1.11
    aghetti
    1.10
    okes
    1.05
    acious
    1.04
    inning
    1.01
    acer
    1.01
    itt
    1.01
    rit
    1.00
    iegel
    1.00
    Activations Density 0.026%

    No Known Activations