© 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. 10-RES-JB
    11. 13871
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer systems and programming

    oai_token-act-pair · gpt-3.5-turbo

    references to errors or issues in software systems

    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
     nurt
    -0.83
     Partnership
    -0.76
     lavish
    -0.75
    ategic
    -0.75
     particip
    -0.74
    orgetown
    -0.71
    icipated
    -0.70
     apprentices
    -0.69
     cultivating
    -0.68
     touring
    -0.68
    POSITIVE LOGITS
     workaround
    1.66
    Solution
    1.48
     Solution
    1.23
     Fixes
    1.23
     fix
    1.22
    Fix
    1.21
    hooting
    1.21
     FIX
    1.20
     disabling
    1.19
    fix
    1.19
    Activations Density 0.569%

    No Known Activations