© 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. 17762
    Prev
    Next
    INDEX
    Explanations

    terms related to qualities or attributes

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to size, performance, and various ideologies

    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
    enium
    -0.65
    arag
    -0.64
    renheit
    -0.64
    ean
    -0.63
    esi
    -0.62
    oka
    -0.60
    ropolis
    -0.60
    xi
    -0.58
    anian
    -0.58
     Cluster
    -0.57
    POSITIVE LOGITS
     considerations
    1.12
     matters
    0.96
     dictates
    0.91
     constraints
    0.90
     mattered
    0.89
     differences
    0.86
     aside
    0.85
     specificity
    0.82
     preced
    0.81
     outweigh
    0.81
    Activations Density 0.477%

    No Known Activations