© 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. 5438
    Prev
    Next
    INDEX
    Explanations

    words related to various career paths or job opportunities

    oai_token-act-pair · gpt-3.5-turbo

    references to careers and professional development

    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
     Oo
    -0.82
     Brotherhood
    -0.65
    ggles
    -0.65
    bite
    -0.60
     Syndicate
    -0.58
     flesh
    -0.58
     partial
    -0.57
    igo
    -0.57
     tribal
    -0.56
     saline
    -0.56
    POSITIVE LOGITS
     careers
    1.19
    schild
    0.74
    rities
    0.74
     Career
    0.73
    chool
    0.71
    ystem
    0.69
     certs
    0.68
    jobs
    0.68
    icht
    0.68
     career
    0.68
    Activations Density 0.011%

    No Known Activations