© 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. 10-RES-JB
    6. 13883
    Prev
    Next
    INDEX
    Explanations

    phrases related to statements or quotes made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    reported speech or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ariel
    -0.82
    ube
    -0.79
     ART
    -0.79
     Siren
    -0.78
     Venus
    -0.76
     violin
    -0.75
     Romantic
    -0.75
     helium
    -0.74
     Prometheus
    -0.74
    ãĤ¢
    -0.74
    POSITIVE LOGITS
    Mc
    2.14
     Mc
    1.75
     McD
    1.71
     McF
    1.71
     McInt
    1.66
     McDonald
    1.65
     McC
    1.64
     McM
    1.64
     McGee
    1.60
     McK
    1.59
    Activations Density 0.280%

    No Known Activations