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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 3567
    Prev
    Next
    INDEX
    Explanations

    numerical values or measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to gaming and entertainment-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omever
    -0.60
     theirs
    -0.54
    every
    -0.53
    instead
    -0.52
    sit
    -0.51
     whoever
    -0.51
     exactly
    -0.51
    depending
    -0.51
     indistinguishable
    -0.51
     countless
    -0.50
    POSITIVE LOGITS
     Profile
    1.06
     âĵĺ
    0.88
     Presents
    0.79
     Brewing
    0.78
     Releases
    0.76
     Calculator
    0.76
     Overview
    0.73
     Forums
    0.70
    âĦ¢:
    0.70
     Quote
    0.69
    Activations Density 0.652%

    No Known Activations