© 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. 2543
    Prev
    Next
    INDEX
    Explanations

    written explanations or descriptions within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to documents or transcripts

    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
    aneers
    -0.92
    alties
    -0.86
    ãĥĺ
    -0.85
    ¨
    -0.82
    entimes
    -0.81
    untu
    -0.81
    Downloadha
    -0.79
    cles
    -0.77
    abilities
    -0.76
    gas
    -0.76
    POSITIVE LOGITS
     rundown
    1.09
     breakdown
    1.07
     synopsis
    0.99
     kicker
    0.98
     excerpt
    0.98
     caveat
    0.91
     overview
    0.90
     reasoning
    0.89
     link
    0.88
     backstory
    0.86
    Activations Density 0.079%

    No Known Activations