© 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. 10-RES-JB
    11. 10998
    Prev
    Next
    INDEX
    Explanations

    instructions or commands for editing files or documents

    oai_token-act-pair · gpt-3.5-turbo

    instructions for editing or updating files and code

    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
    agher
    -0.72
     calcul
    -0.68
    rush
    -0.66
     Confederacy
    -0.64
     Syndrome
    -0.64
     jugg
    -0.62
    ereo
    -0.62
     TVs
    -0.61
     Telesc
    -0.61
    ä¹ĭ
    -0.61
    POSITIVE LOGITS
     ~/.
    1.23
     config
    1.10
     sudo
    1.08
     snippet
    1.07
     configuration
    1.00
     file
    1.00
     alias
    0.96
     aliases
    0.95
     directive
    0.95
     declarations
    0.93
    Activations Density 0.154%

    No Known Activations