© 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. 9511
    Prev
    Next
    INDEX
    Explanations

    the phrase "secondary market" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to secondary markets and associated concepts

    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
    ebus
    -0.74
    ============
    -0.74
    âĸĪâĸĪ
    -0.71
    âĸĪâĸĪâĸĪâĸĪ
    -0.68
    ===
    -0.68
    ========
    -0.66
    Roberts
    -0.65
     Archdemon
    -0.64
    Deal
    -0.64
     Liberties
    -0.63
    POSITIVE LOGITS
    secondary
    1.22
     secondary
    1.12
     Secondary
    0.88
     tert
    0.87
    ocre
    0.83
    primary
    0.83
     primary
    0.77
     mosqu
    0.76
    artifacts
    0.75
    pole
    0.71
    Activations Density 0.009%

    No Known Activations