© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 10707
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to action or state

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating existence or ongoing states

    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
     weave
    -0.69
     Spray
    -0.63
     Jungle
    -0.62
     Goods
    -0.62
     Turns
    -0.61
     CTR
    -0.61
     Indie
    -0.59
     palms
    -0.58
     spills
    -0.58
     Steps
    -0.58
    POSITIVE LOGITS
    å°Ĩ
    0.88
    ered
    0.84
    èª
    0.82
    ifiable
    0.81
    ened
    0.79
    mint
    0.77
    ãĥ´ãĤ¡
    0.77
    ukong
    0.76
    outed
    0.75
    à©
    0.73
    Activations Density 0.219%

    No Known Activations