© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 24516
    Prev
    Next
    INDEX
    Explanations

    mentions of positions that need to be filled or are available, particularly vacancies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to vacancies and open positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bal
    -0.79
    pper
    -0.67
    jer
    -0.63
    rid
    -0.63
    âĵĺ
    -0.62
    GER
    -0.62
    hran
    -0.62
    osterone
    -0.61
    hod
    -0.60
    obby
    -0.60
    POSITIVE LOGITS
     vacancies
    1.38
     vacancy
    1.32
     listings
    0.90
     openings
    0.89
    ancies
    0.88
     vacated
    0.88
    riages
    0.72
    ellen
    0.71
     positions
    0.71
    acies
    0.69
    Activations Density 0.014%

    No Known Activations