© 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. 20165
    Prev
    Next
    INDEX
    Explanations

    legal terms and court-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    legal terminology and references to court cases

    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
    obal
    -0.76
     capsule
    -0.74
     ascending
    -0.73
    icrobial
    -0.69
     vow
    -0.68
     orbit
    -0.66
     brew
    -0.66
     heals
    -0.65
     transition
    -0.64
     belts
    -0.64
    POSITIVE LOGITS
    Attorney
    0.99
    emphasis
    0.90
     appellant
    0.86
     §§
    0.84
     Amnesty
    0.82
     Defendants
    0.82
    ¤
    0.81
    sup
    0.80
     Defendant
    0.80
     supra
    0.80
    Activations Density 0.742%

    No Known Activations