© 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. 7-RES-JB
    11. 17960
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features that make a product suitable for specific tasks or environments

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to outdoor or small-scale applications

    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
     Reverend
    -0.75
    mir
    -0.72
     affirmative
    -0.71
     Zel
    -0.71
     translated
    -0.66
     translation
    -0.66
    rant
    -0.66
     Negro
    -0.66
    Ry
    -0.65
    lation
    -0.64
    POSITIVE LOGITS
     versatility
    0.89
    naissance
    0.88
     crave
    0.86
    erning
    0.83
     applications
    0.79
     DIY
    0.77
     adventurous
    0.77
     versatile
    0.76
     encount
    0.76
     outdoor
    0.76
    Activations Density 1.354%

    No Known Activations