© 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. 8-RES-JB
    11. 15198
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational decisions and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to governmental or organizational actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     magazines
    -0.81
    essor
    -0.78
     selves
    -0.77
    iability
    -0.69
     corpses
    -0.68
     haun
    -0.68
     segments
    -0.67
     liter
    -0.67
     perished
    -0.67
     capacities
    -0.66
    POSITIVE LOGITS
     prompted
    0.85
    ktop
    0.84
     spurred
    0.81
     reversal
    0.80
     welcome
    0.78
    quickShipAvailable
    0.78
     bullish
    0.77
    UMP
    0.77
    LEASE
    0.77
    ARM
    0.76
    Activations Density 0.484%

    No Known Activations