© 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. 18428
    Prev
    Next
    INDEX
    Explanations

    phrases related to secretive or undercover activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to covert and clandestine operations

    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
    idian
    -0.74
    ð
    -0.73
    nesota
    -0.73
     Pwr
    -0.72
    ordan
    -0.72
    shield
    -0.71
    Demand
    -0.71
    amaz
    -0.69
    annis
    -0.67
    Äį
    -0.67
    POSITIVE LOGITS
    arial
    1.03
     annex
    0.87
     stash
    0.84
     ops
    0.83
     operations
    0.77
    ively
    0.76
    ly
    0.76
     CIA
    0.76
     recordings
    0.75
    aneously
    0.75
    Activations Density 0.064%

    No Known Activations