© 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. 10-RES-JB
    11. 17400
    Prev
    Next
    INDEX
    Explanations

    positions or roles within organizations and jobs related to various industries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of job roles and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioxide
    -0.78
    lag
    -0.68
     Causes
    -0.68
     Rx
    -0.68
     Peb
    -0.66
    amaz
    -0.66
    Wave
    -0.65
    veland
    -0.65
    phrine
    -0.63
     grains
    -0.62
    POSITIVE LOGITS
     responsibilities
    1.07
     assignments
    1.06
     vacant
    1.03
     assigned
    1.03
     vacancies
    1.00
     assignment
    0.97
     specialization
    0.97
     vacated
    0.97
     duties
    0.96
     occupied
    0.96
    Activations Density 0.191%

    No Known Activations