© 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. 2-RES-JB
    11. 19737
    Prev
    Next
    INDEX
    Explanations

    terms related to employment and the job market

    oai_token-act-pair · gpt-3.5-turbo

    references to the workforce

    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
    gran
    -0.83
    ocular
    -0.75
    osp
    -0.72
     Hussein
    -0.70
    rah
    -0.66
    ion
    -0.66
    osis
    -0.64
    emn
    -0.64
    election
    -0.64
    abre
    -0.64
    POSITIVE LOGITS
     workforce
    1.14
    ãĤ©
    0.72
     unemployed
    0.69
     Quarterly
    0.68
     unemploy
    0.68
     Wage
    0.67
     Builder
    0.66
    Builder
    0.66
     Employ
    0.65
    KK
    0.65
    Activations Density 0.005%

    No Known Activations