© 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. 22475
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals named "Ser" followed by a specific pattern or number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ser" followed by a number, likely indicating the focus on a specific individual with that title or name

    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
    INGTON
    -0.87
    ORN
    -0.82
    Rated
    -0.80
    ESCO
    -0.76
    AUT
    -0.75
    OWS
    -0.73
    PUT
    -0.72
    enegger
    -0.71
    è£ħ
    -0.70
    ELS
    -0.70
    POSITIVE LOGITS
    otonin
    1.01
    geant
    1.01
    iffs
    0.97
    ials
    0.95
    onial
    0.88
    rha
    0.88
    uitous
    0.87
    rano
    0.86
    archs
    0.86
    mons
    0.84
    Activations Density 0.011%

    No Known Activations