© 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. 6-RES-JB
    11. 15153
    Prev
    Next
    INDEX
    Explanations

    phrases describing or explaining something in a formal or detailed manner

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the word "the" and contextually significant descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     depended
    -0.63
    ijn
    -0.60
    lease
    -0.59
     Md
    -0.58
    hew
    -0.56
    aintain
    -0.56
    amba
    -0.56
    astics
    -0.55
    hops
    -0.54
    redo
    -0.54
    POSITIVE LOGITS
    MpServer
    0.82
    DragonMagazine
    0.78
     Situation
    0.76
     situation
    0.75
     actions
    0.73
    quickShipAvailable
    0.72
     qualities
    0.71
     virtues
    0.71
     "$:/
    0.71
     inaction
    0.70
    Activations Density 0.198%

    No Known Activations