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. 11521
    Prev
    Next
    INDEX
    Explanations

    proper nouns, possibly names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named "Den" or "Den-o."

    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
    EED
    -0.67
    avorite
    -0.67
    olicy
    -0.66
     behav
    -0.60
    RESULTS
    -0.60
     independently
    -0.59
     dys
    -0.58
    EH
    -0.58
    ROM
    -0.58
    acebook
    -0.58
    POSITIVE LOGITS
    ning
    1.03
    izens
    1.00
    unci
    0.99
    ving
    0.98
    wald
    0.96
    heim
    0.92
    ver
    0.89
    zen
    0.89
    izen
    0.88
    unciation
    0.86
    Activations Density 0.009%

    No Known Activations