© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 19650
    Prev
    Next
    INDEX
    Explanations

    mentions of job-related terms and activities such as job training, employment, resumes, and job satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    references to jobs and employment-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oo
    -0.77
     Flavoring
    -0.76
     Bulg
    -0.70
     Revision
    -0.64
     Blast
    -0.63
    anwhile
    -0.63
    theless
    -0.62
    orp
    -0.62
    stals
    -0.62
     rays
    -0.62
    POSITIVE LOGITS
    anooga
    0.87
     seeker
    0.84
    seekers
    0.80
    job
    0.80
    days
    0.79
    jobs
    0.77
     sched
    0.76
    uilt
    0.75
    fell
    0.74
    Builder
    0.74
    Activations Density 0.037%

    No Known Activations