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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 20609
    Prev
    Next
    INDEX
    Explanations

    specific information related to individuals, such as names, ages, and locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ownership or association, particularly in reference to people or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TPP
    -0.79
    DragonMagazine
    -0.73
    Created
    -0.73
    norm
    -0.72
     exerted
    -0.70
    archy
    -0.70
    Episode
    -0.69
    TIME
    -0.69
    matic
    -0.67
    [_
    -0.67
    POSITIVE LOGITS
     Pleasant
    1.24
     Arlington
    1.21
     Newtown
    1.20
     Plymouth
    1.17
     Queens
    1.16
     Wilmington
    1.15
     Clarks
    1.15
     Bronx
    1.15
     Bellev
    1.15
     Minneapolis
    1.15
    Activations Density 0.104%

    No Known Activations