© 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. 4-RES-JB
    11. 6138
    Prev
    Next
    INDEX
    Explanations

    opportunities for various purposes like revenue, employment, business, and improvement

    oai_token-act-pair · gpt-3.5-turbo

    references to business and economic opportunities

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

    No Comments

    Negative Logits
    ded
    -0.81
    idine
    -0.76
    head
    -0.71
    netflix
    -0.71
    roy
    -0.70
    amed
    -0.69
    tag
    -0.69
    aida
    -0.67
    sis
    -0.67
    gear
    -0.66
    POSITIVE LOGITS
     opportunities
    1.41
     Opportun
    1.22
     opportunity
    1.10
     Opportunity
    1.08
    izons
    0.83
     openings
    0.80
    urities
    0.80
     avenues
    0.75
     prospects
    0.75
     hazards
    0.75
    Activations Density 0.015%

    No Known Activations