© 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. 2211
    Prev
    Next
    INDEX
    Explanations

    text related to specific numerical values or technical details

    oai_token-act-pair · gpt-3.5-turbo

    terms related to norms, constructs, and societal standards

    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
     Banner
    -0.67
    HOME
    -0.61
     Normandy
    -0.54
     vulnerability
    -0.53
     distraction
    -0.52
    etsk
    -0.50
     tattoo
    -0.47
    Dialog
    -0.47
     Redemption
    -0.46
    exit
    -0.46
    POSITIVE LOGITS
    cially
    1.27
    ifully
    1.15
    imately
    1.11
    ificantly
    1.11
    ually
    1.11
    ivably
    1.08
    arily
    1.08
    pecially
    1.07
    ically
    1.07
    ially
    1.06
    Activations Density 0.518%

    No Known Activations