© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12021
    Prev
    Next
    INDEX
    Explanations

    phrases related to two-way interactions or contracts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to bilateral or reciprocal agreements

    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
     Gru
    -0.75
    uster
    -0.71
     mechan
    -0.67
    usters
    -0.66
    asts
    -0.65
    acons
    -0.62
     newsletters
    -0.61
     stakes
    -0.61
     concent
    -0.61
     antitrust
    -0.61
    POSITIVE LOGITS
    finding
    1.06
    PASS
    0.98
    way
    0.96
    fare
    0.88
    bye
    0.87
    sey
    0.84
    bo
    0.82
    frame
    0.79
    bos
    0.79
    point
    0.78
    Activations Density 0.013%

    No Known Activations