© 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. 10-RES-JB
    11. 16971
    Prev
    Next
    INDEX
    Explanations

    words related to a specific type of item or product, specifically bags

    oai_token-act-pair · gpt-3.5-turbo

    words associated with visibility and perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    --------------------------------------------------------
    -0.65
     rule
    -0.61
     Carly
    -0.61
    cone
    -0.60
    mess
    -0.60
     clutch
    -0.58
     overpower
    -0.58
    chall
    -0.57
     passer
    -0.56
    xon
    -0.55
    POSITIVE LOGITS
    iera
    1.15
    iew
    1.10
    isible
    1.09
    isions
    1.02
    aldi
    1.02
    olution
    1.02
    ision
    1.02
    irus
    1.01
    entric
    1.01
    ISION
    0.99
    Activations Density 0.041%

    No Known Activations