© 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. 8-RES-JB
    11. 4997
    Prev
    Next
    INDEX
    Explanations

    lines of code commands related to software development

    oai_token-act-pair · gpt-3.5-turbo

    negative command or debugging terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hanson
    -0.71
     Emmy
    -0.70
     Norris
    -0.70
     Yaz
    -0.70
     Jasper
    -0.69
     Phelps
    -0.68
     Gunn
    -0.68
     Maher
    -0.68
     Mek
    -0.68
     Tyler
    -0.67
    POSITIVE LOGITS
    mode
    1.20
    notation
    1.15
    modules
    1.14
    directory
    1.13
    tools
    1.11
    tree
    1.11
    generic
    1.10
    sama
    1.10
    wrapper
    1.10
    cache
    1.08
    Activations Density 0.116%

    No Known Activations