© 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. 12817
    Prev
    Next
    INDEX
    Explanations

    mentions of federal legal actions or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to federal laws and legal systems

    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
    enger
    -0.74
    ktop
    -0.71
    lihood
    -0.71
    enes
    -0.70
    apist
    -0.69
    ppard
    -0.68
    upper
    -0.66
    edin
    -0.65
    aming
    -0.65
    vu
    -0.65
    POSITIVE LOGITS
     agencies
    1.05
    ism
    0.90
     regulators
    0.86
     agency
    0.86
     dollars
    0.86
     prosecutors
    0.86
     contractors
    0.85
     agents
    0.85
     officials
    0.85
     Reserve
    0.84
    Activations Density 0.029%

    No Known Activations