Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 18903
    Prev
    Next
    INDEX
    Explanations

    specific job titles for specific professions or roles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to management and organizational roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assian
    -0.74
    oven
    -0.72
    alach
    -0.71
     Effect
    -0.67
     Meal
    -0.64
    inational
    -0.63
    ablish
    -0.63
    enge
    -0.63
    ostic
    -0.63
    #$
    -0.63
    POSITIVE LOGITS
     director
    0.94
     manager
    0.91
     officials
    0.91
     chief
    0.88
     coordinator
    0.88
     circles
    0.86
    wat
    0.85
     adviser
    0.84
     spokesman
    0.82
     headquarters
    0.81
    Activations Density 0.317%

    No Known Activations