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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22615
    Prev
    Next
    INDEX
    Explanations

    demonstratives or pronouns referring to a specific group of people

    oai_token-act-pair · gpt-3.5-turbo

    references to specific groups of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILY
    -0.78
    ob
    -0.74
    enegger
    -0.72
    inson
    -0.70
    onis
    -0.70
    ointment
    -0.69
     Minion
    -0.68
    Luck
    -0.67
     Resolution
    -0.67
    Drag
    -0.63
    POSITIVE LOGITS
     kinds
    0.96
     pesky
    0.85
     sorts
    0.84
     wishing
    0.80
     surveyed
    0.79
     favoring
    0.75
     interested
    0.74
     attending
    0.73
     who
    0.73
     aspects
    0.72
    Activations Density 0.068%

    No Known Activations