© 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. 24226
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or law enforcement activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "seized" and related forms

    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
    asin
    -0.68
    ctory
    -0.68
    tem
    -0.65
    iden
    -0.65
    proxy
    -0.65
     offic
    -0.64
    atten
    -0.64
    itte
    -0.64
     Kier
    -0.62
    nder
    -0.62
    POSITIVE LOGITS
     seized
    1.12
     seize
    0.99
     seizing
    0.99
     seizure
    0.88
     seizures
    0.86
    iffs
    0.84
     confiscated
    0.83
    ilage
    0.76
     forfeiture
    0.76
    ãĥĥãĥĪ
    0.75
    Activations Density 0.012%

    No Known Activations