© 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. 4-RES-JB
    11. 22191
    Prev
    Next
    INDEX
    Explanations

    phrases indicating approval or support

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to voting in favor of proposals or legislation

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

    No Comments

    Negative Logits
     Brist
    -0.71
    tis
    -0.69
     Gorge
    -0.64
    LES
    -0.64
    ı
    -0.63
    legged
    -0.63
    ridges
    -0.63
    liam
    -0.61
     Pist
    -0.61
     Torn
    -0.60
    POSITIVE LOGITS
    itism
    1.25
    ability
    0.79
    ative
    0.76
     favoring
    0.75
    ably
    0.75
    ality
    0.74
    uate
    0.72
    parency
    0.71
    ibility
    0.71
    atives
    0.71
    Activations Density 0.016%

    No Known Activations