© 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. 10-RES-JB
    11. 6684
    Prev
    Next
    INDEX
    Explanations

    references to deception, dishonesty, and legal matters involving lying or pleading guilty

    oai_token-act-pair · gpt-3.5-turbo

    statements involving falsehoods or lying in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     priced
    -0.72
     à¨
    -0.70
    gra
    -0.70
    anty
    -0.69
    wagon
    -0.69
    âĸ¬
    -0.68
    -->
    -0.67
    à©
    -0.65
    winner
    -0.64
     somew
    -0.63
    POSITIVE LOGITS
     investigators
    1.56
     FBI
    1.16
    FBI
    1.15
     reporters
    1.14
     prosecutors
    1.12
     interrog
    1.11
     witnesses
    1.11
     detectives
    1.10
     authorities
    1.10
     Investigators
    1.09
    Activations Density 0.362%

    No Known Activations