© 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. 16411
    Prev
    Next
    INDEX
    Explanations

    legal terms related to police actions and civil rights

    oai_token-act-pair · gpt-3.5-turbo

    terms related to excessiveness, unnecessary actions, and violations of rights

    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
    ector
    -0.86
    ect
    -0.75
    asio
    -0.75
    ebus
    -0.73
    ript
    -0.71
    imore
    -0.71
    ienne
    -0.70
    olitan
    -0.68
    ection
    -0.67
    atform
    -0.67
    POSITIVE LOGITS
     burden
    1.00
     burdens
    0.92
     enrichment
    0.91
     delay
    0.87
     delays
    0.85
     expense
    0.85
     hardship
    0.84
     duplication
    0.83
     reliance
    0.79
     pregnancies
    0.78
    Activations Density 0.154%

    No Known Activations