© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1856
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to technology and companies, such as "Desmond", "Activision", "Agility", and "Alexa"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to companies and their products

    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
    erman
    -0.87
    eter
    -0.86
    lers
    -0.86
    paren
    -0.85
    sheet
    -0.84
    ner
    -0.82
    ning
    -0.82
    iaries
    -0.79
    enhagen
    -0.79
    ened
    -0.78
    POSITIVE LOGITS
     GOODMAN
    0.85
    ERY
    0.74
    phia
    0.71
    IPS
    0.68
    ãĥŀ
    0.67
    avis
    0.65
     Thatcher
    0.65
    BILITY
    0.64
     Amend
    0.64
     Viper
    0.63
    Activations Density 0.035%

    No Known Activations