© 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. 3-RES-JB
    11. 15052
    Prev
    Next
    INDEX
    Explanations

    several mentions of directories in a technical context, possibly related to software development

    oai_token-act-pair · gpt-3.5-turbo

    references to file system directories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acted
    -0.89
    acting
    -0.86
    laws
    -0.78
    rained
    -0.77
    uca
    -0.77
    lev
    -0.72
    fle
    -0.71
    ake
    -0.71
    oria
    -0.69
    akening
    -0.67
    POSITIVE LOGITS
     directory
    1.03
     directories
    1.01
     descriptor
    0.89
     Directory
    0.87
    directory
    0.83
     cellar
    0.81
     filesystem
    0.77
     folders
    0.76
     folder
    0.76
     separ
    0.75
    Activations Density 0.010%

    No Known Activations