© 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. 7549
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement personnel

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement personnel

    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
    topic
    -0.95
    Pad
    -0.78
    projects
    -0.76
    Hop
    -0.75
    aired
    -0.75
    leaf
    -0.73
    ten
    -0.72
    term
    -0.72
    ranged
    -0.72
    ital
    -0.70
    POSITIVE LOGITS
     corrid
    1.05
     policemen
    0.90
     Polic
    0.90
     policeman
    0.87
     conduc
    0.81
    uterte
    0.77
    anguage
    0.77
     stationed
    0.77
     nab
    0.71
    yrights
    0.70
    Activations Density 0.005%

    No Known Activations