© 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. 7285
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific individuals or names

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals involved in high-profile legal cases, particularly related to police incidents

    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
    achusetts
    -0.95
    ovie
    -0.94
    llor
    -0.87
    manship
    -0.81
    ateur
    -0.78
    cro
    -0.78
    rina
    -0.75
    kit
    -0.75
    tle
    -0.75
    enium
    -0.74
    POSITIVE LOGITS
     Saga
    0.68
     Garner
    0.68
     detox
    0.66
     Jungle
    0.62
     Beng
    0.62
     pads
    0.62
     Islanders
    0.62
    zl
    0.62
     Pound
    0.62
     Islands
    0.62
    Activations Density 0.023%

    No Known Activations