© 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. 15719
    Prev
    Next
    INDEX
    Explanations

    numerical data or measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to performance metrics or comparisons in technology or equipment

    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
     ÂŃ
    -0.57
     attendees
    -0.56
    oused
    -0.54
    Visit
    -0.54
    ombs
    -0.54
    Words
    -0.54
    Names
    -0.53
    Listen
    -0.53
    boarding
    -0.51
    ideshow
    -0.51
    POSITIVE LOGITS
     MUCH
    1.34
     slower
    1.18
     marginally
    1.13
     weaker
    1.10
     considerably
    1.09
     alot
    1.09
     slightly
    1.08
     faster
    1.04
     smoother
    1.01
     cheaper
    1.01
    Activations Density 0.578%

    No Known Activations