© 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. 9955
    Prev
    Next
    INDEX
    Explanations

    legal terms related to court proceedings

    oai_token-act-pair · gpt-3.5-turbo

    words related to legal appeals and decisions

    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
    inki
    -0.70
    obyl
    -0.66
    oother
    -0.62
    onna
    -0.61
    stones
    -0.60
    holes
    -0.58
    rians
    -0.57
    atform
    -0.57
    uds
    -0.56
    hene
    -0.55
    POSITIVE LOGITS
     his
    0.99
     anyway
    0.91
     anyways
    0.90
     her
    0.85
     accordingly
    0.82
     everything
    0.78
     their
    0.77
     them
    0.76
     it
    0.75
     him
    0.75
    Activations Density 0.320%

    No Known Activations