© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3980
    Prev
    Next
    INDEX
    Explanations

    phrases related to various types of resources

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ker
    -0.78
    ews
    -0.72
    alone
    -0.70
     Negative
    -0.69
    esta
    -0.65
     vow
    -0.64
    ership
    -0.63
    arella
    -0.63
    reads
    -0.62
     commercial
    -0.62
    POSITIVE LOGITS
     resources
    1.03
     resource
    1.00
     Resource
    0.93
    resource
    0.87
    Resources
    0.85
    Resource
    0.84
     Resources
    0.83
    cit
    0.78
    ãĤ¼ãĤ¦ãĤ¹
    0.78
     allocation
    0.76
    Activations Density 0.006%

    No Known Activations