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. 3-RES-JB
    6. 2464
    Prev
    Next
    INDEX
    Explanations

    professional roles or positions within different organizations

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles of people in positions of authority or leadership

    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
    adies
    -0.76
     flock
    -0.68
    burning
    -0.67
     boulder
    -0.67
    oping
    -0.66
     needle
    -0.65
    eros
    -0.65
     porch
    -0.63
    umatic
    -0.63
    oked
    -0.63
    POSITIVE LOGITS
     Loren
    0.77
     Shaun
    0.76
    HAEL
    0.72
     Ernest
    0.72
     extraord
    0.72
     Alan
    0.71
     chairman
    0.70
     Laura
    0.70
     director
    0.67
     Rebecca
    0.67
    Activations Density 0.358%

    No Known Activations