© 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. 2-RES-JB
    6. 11782
    Prev
    Next
    INDEX
    Explanations

    legal terms related to alternatives or substitutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal terms, particularly those involving asset forfeiture

    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
     oats
    -0.75
    eway
    -0.70
     Dynamics
    -0.70
    romy
    -0.70
    raz
    -0.68
    tailed
    -0.66
     Conduct
    -0.64
    izoph
    -0.64
    acia
    -0.63
     Wolves
    -0.62
    POSITIVE LOGITS
    xual
    0.86
    terday
    0.83
    atchewan
    0.82
    olean
    0.79
     lieu
    0.79
    uit
    0.77
    chal
    0.76
    clair
    0.71
    ppelin
    0.71
    itute
    0.70
    Activations Density 0.016%

    No Known Activations