© 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. 11-RES-JB
    11. 10117
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or proceedings

    oai_token-act-pair · gpt-3.5-turbo

    words associated with legal and investigative processes

    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
     Spend
    -0.63
    edia
    -0.63
    verse
    -0.60
     detrim
    -0.56
     sacrific
    -0.55
    dp
    -0.55
     IPM
    -0.54
     ItemLevel
    -0.53
     Yourself
    -0.52
    amps
    -0.52
    POSITIVE LOGITS
     exists
    1.56
     existed
    1.35
     ensued
    1.29
     emerges
    1.28
     awaits
    1.26
     emerged
    1.25
     arises
    1.17
     occurred
    1.16
     exist
    1.15
     awaited
    1.15
    Activations Density 0.455%

    No Known Activations