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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6564
    Prev
    Next
    INDEX
    Explanations

    brand names related to various products or services

    oai_token-act-pair · gpt-3.5-turbo

    mentions of popular brands or products

    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
    istically
    -0.83
    ounter
    -0.75
    ilitary
    -0.72
    opausal
    -0.69
     fireworks
    -0.66
     perjury
    -0.66
    ccording
    -0.66
    izes
    -0.65
     retri
    -0.64
    >>>>>>>>
    -0.64
    POSITIVE LOGITS
    Berry
    0.96
    kit
    0.92
    fit
    0.92
    down
    0.91
    kat
    0.91
    finger
    0.90
    enh
    0.89
    Plex
    0.88
    Stream
    0.88
     Shack
    0.87
    Activations Density 0.151%

    No Known Activations