© 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. 1-RES-JB
    11. 3623
    Prev
    Next
    INDEX
    Explanations

    commands related to setting up development environments or paths

    oai_token-act-pair · gpt-3.5-turbo

    technical commands and file paths related to programming or software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etsy
    -0.86
    ouver
    -0.74
    deals
    -0.74
    hra
    -0.73
    axy
    -0.73
    raits
    -0.72
    axies
    -0.71
    enes
    -0.70
    ossal
    -0.70
    iday
    -0.70
    POSITIVE LOGITS
     sshd
    0.91
     foo
    0.90
     ssh
    0.86
     gcc
    0.84
     ~/.
    0.83
     Emacs
    0.82
     debugger
    0.82
     grep
    0.82
     vim
    0.81
     src
    0.80
    Activations Density 0.436%

    No Known Activations