© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 22545
    Prev
    Next
    INDEX
    Explanations

    mentions of legal entities i.e., courts

    oai_token-act-pair · gpt-3.5-turbo

    references to legal courts

    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
     ana
    -0.67
     Austral
    -0.63
     Stronghold
    -0.63
    igun
    -0.62
     NATO
    -0.62
    ACTED
    -0.62
     Laf
    -0.60
     Hab
    -0.60
     OS
    -0.60
     Camb
    -0.59
    POSITIVE LOGITS
    hip
    0.91
    assic
    0.88
     courts
    0.84
    wright
    0.82
    auld
    0.82
    yer
    0.81
    ices
    0.81
    esan
    0.80
    icing
    0.79
    ide
    0.79
    Activations Density 0.010%

    No Known Activations