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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 11217
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal procedures involving asset forfeiture

    oai_token-act-pair · gpt-3.5-turbo

    terms related to asset forfeiture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ases
    -0.74
    iatus
    -0.73
    asin
    -0.72
    asing
    -0.70
    rio
    -0.70
    ase
    -0.67
    rame
    -0.67
    inx
    -0.65
    ased
    -0.65
    hat
    -0.65
    POSITIVE LOGITS
     forfeiture
    1.46
     forfe
    1.45
     forfeit
    1.39
    itures
    0.89
     seizures
    0.80
    lynn
    0.66
     unaccount
    0.66
    mary
    0.66
     seizure
    0.65
    ilage
    0.64
    Activations Density 0.015%

    No Known Activations