© 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. 9293
    Prev
    Next
    INDEX
    Explanations

    names containing the substring "Vel" and related words

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals or organizations

    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
    éļ
    -0.74
    ãĥĩãĤ£
    -0.73
     Territories
    -0.73
    é¾įå
    -0.71
    éĹĺ
    -0.71
    à©
    -0.70
    FTWARE
    -0.67
    ardless
    -0.66
    åij
    -0.66
    ãĤ´ãĥ³
    -0.65
    POSITIVE LOGITS
    ocity
    1.19
    atility
    0.99
    ength
    0.94
     corrid
    0.92
    iver
    0.92
    imar
    0.88
    ulner
    0.87
    ibr
    0.87
    uxe
    0.85
    idays
    0.81
    Activations Density 0.009%

    No Known Activations