© 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. 20871
    Prev
    Next
    INDEX
    Explanations

    specific names and titles that are commonly found in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain conjunctions and articles frequently used in context

    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
    wcs
    -0.75
    ufact
    -0.72
    uscript
    -0.70
    istar
    -0.70
    icularly
    -0.68
    ugi
    -0.68
    ussions
    -0.65
    rawdownloadcloneembedreportprint
    -0.65
    oslav
    -0.64
    enance
    -0.64
    POSITIVE LOGITS
    ãĥīãĥ©
    0.60
     Federation
    0.60
     Labrador
    0.58
     parap
    0.56
    ãĥ¼ãĥĨ
    0.54
     Fut
    0.54
     riches
    0.53
    enced
    0.53
     Falcon
    0.53
     vacuum
    0.53
    Activations Density 0.632%

    No Known Activations