© 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. 4-RES-JB
    11. 6379
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal processes and regulations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "pro" or support for a certain approach or perspective

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

    No Comments

    Negative Logits
     needles
    -0.74
    inia
    -0.70
     Halls
    -0.69
     halls
    -0.66
    BuyableInstoreAndOnline
    -0.66
    worms
    -0.64
     Cornell
    -0.63
     Beir
    -0.62
     Hollow
    -0.62
     fault
    -0.62
    POSITIVE LOGITS
    digy
    1.26
    secut
    1.26
    blems
    1.23
    ceed
    1.16
    gression
    1.09
    secution
    1.07
    posal
    1.04
    gressive
    1.03
    portion
    1.00
    poses
    0.96
    Activations Density 0.016%

    No Known Activations