© 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. 0-RES-JB
    11. 11921
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing a specific point or aspect

    oai_token-act-pair · gpt-3.5-turbo

    phrases that highlight significant exceptions or particular cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fal
    -0.58
    Base
    -0.56
    uclear
    -0.55
    ral
    -0.53
    Detailed
    -0.52
    mpire
    -0.52
    ory
    -0.52
    uity
    -0.52
     Upload
    -0.52
    usp
    -0.51
    POSITIVE LOGITS
     especially
    3.21
    especially
    3.00
     particularly
    2.72
    particularly
    2.59
     Especially
    2.20
    Especially
    2.01
     Particularly
    1.80
     notably
    1.47
     chiefly
    1.35
     specifically
    1.26
    Activations Density 0.021%

    No Known Activations