© 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. 11-RES-JB
    6. 54
    Prev
    Next
    INDEX
    Explanations

    references to laws or legal matters

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cros
    -0.73
    xit
    -0.69
    ARCH
    -0.67
    ixel
    -0.66
    ricular
    -0.64
     Expedition
    -0.63
    Mid
    -0.62
     sqor
    -0.61
     Velocity
    -0.61
     Rubber
    -0.61
    POSITIVE LOGITS
     enforcement
    1.44
    lessness
    1.36
    suit
    1.35
    suits
    1.27
     abiding
    1.26
    fulness
    1.24
    enforcement
    1.22
    yer
    1.13
     Enforcement
    1.13
     prohibiting
    1.11
    Activations Density 0.057%

    No Known Activations