Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 3943
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to technology or companies

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, likely focusing on a prominent public figure

    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
     Occupations
    -0.91
    IUM
    -0.78
    HER
    -0.72
    OLOGY
    -0.69
     WATCH
    -0.69
    OPLE
    -0.66
    UAL
    -0.65
    gerald
    -0.64
    Condition
    -0.64
     LIA
    -0.64
    POSITIVE LOGITS
    anche
    1.25
    itzer
    1.25
    asts
    1.14
    anch
    1.08
    ocking
    1.05
    adder
    1.04
    anco
    1.03
    asted
    1.01
    anches
    0.99
    adders
    0.98
    Activations Density 0.011%

    No Known Activations