© 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. 8-RES-JB
    11. 7008
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to specific products or applications

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to aerial technology and drone applications

    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
    mir
    -0.74
     Reverend
    -0.73
    rant
    -0.71
    Ry
    -0.71
     affirmative
    -0.69
    xe
    -0.66
     Zel
    -0.65
    anon
    -0.64
    lation
    -0.64
    named
    -0.63
    POSITIVE LOGITS
     crave
    0.86
     adventurous
    0.84
     versatility
    0.82
     outdoor
    0.79
     needing
    0.79
    erning
    0.78
     emergencies
    0.77
     brainstorm
    0.76
     DIY
    0.76
     budgets
    0.76
    Activations Density 0.912%

    No Known Activations