© 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. 3-RES-JB
    11. 623
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically those starting with "Ret"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Retina" or words related to advanced display technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tips
    -0.88
    é¾įåĸļ士
    -0.70
    ãĥ¼ãĥĨ
    -0.69
    EngineDebug
    -0.66
    hower
    -0.66
    STD
    -0.66
    è£ħ
    -0.65
    ãģĨ
    -0.64
     hearts
    -0.63
    INESS
    -0.63
    POSITIVE LOGITS
    ention
    1.05
    rieve
    1.04
    rieving
    1.01
    ribut
    1.00
    ired
    0.99
    ract
    0.93
    irement
    0.92
    reating
    0.91
    rieved
    0.91
    ribution
    0.89
    Activations Density 0.006%

    No Known Activations