© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 1795
    Prev
    Next
    INDEX
    Explanations

    software development instructions and file manipulation commands

    oai_token-act-pair · gpt-3.5-turbo

    elements related to configuration files and setup instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     funer
    -0.81
     discriminating
    -0.76
     discriminate
    -0.76
     dancers
    -0.74
    rosso
    -0.74
     salute
    -0.74
    andowski
    -0.69
     escort
    -0.67
     parap
    -0.67
     contestants
    -0.67
    POSITIVE LOGITS
     folder
    1.40
     ~/.
    1.39
     file
    1.26
    folder
    1.25
     ~/
    1.13
     directory
    1.11
    :\
    1.11
    file
    1.09
     File
    1.09
    directory
    1.06
    Activations Density 0.379%

    No Known Activations