© 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. 7137
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, dates, events, and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to song lyrics or musical content

    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
    whatever
    -0.64
     Pediatrics
    -0.61
     Sven
    -0.60
    udic
    -0.59
    —"
    -0.59
     Qiao
    -0.57
     ÂŃ
    -0.57
     Obj
    -0.55
     âĶľ
    -0.54
     Tuls
    -0.53
    POSITIVE LOGITS
    SourceFile
    0.76
    Interstitial
    0.64
    unte
    0.62
    rote
    0.59
    otions
    0.58
    english
    0.58
    ivia
    0.56
     homegrown
    0.55
    interstitial
    0.55
    Unknown
    0.54
    Activations Density 1.521%

    No Known Activations