© 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. 2-RES-JB
    11. 11077
    Prev
    Next
    INDEX
    Explanations

    mentions of opportunities or chances for something to happen or be done

    oai_token-act-pair · gpt-3.5-turbo

    references to opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sis
    -0.73
    hemat
    -0.69
    bane
    -0.68
    uster
    -0.68
    ijk
    -0.67
    ric
    -0.67
    brand
    -0.66
    tag
    -0.66
    zzy
    -0.65
    head
    -0.64
    POSITIVE LOGITS
     opportunity
    1.26
     opportunities
    1.17
     Opportun
    1.08
     Opportunity
    1.08
    llor
    0.83
    ossibility
    0.80
    urities
    0.78
     afforded
    0.77
     seekers
    0.76
    ounter
    0.73
    Activations Density 0.019%

    No Known Activations