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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    6. 17170
    Prev
    Next
    INDEX
    Explanations

    instances of the word "American"

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or entities with "American" in their names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idious
    -0.75
    pots
    -0.68
    elled
    -0.67
    acca
    -0.67
    worldly
    -0.66
    ologies
    -0.66
    ets
    -0.64
    enser
    -0.63
    poons
    -0.63
    aido
    -0.63
    POSITIVE LOGITS
     Psychological
    1.12
     Psychiatric
    1.08
     Association
    1.02
     Federation
    0.99
     Society
    0.99
     Mathemat
    0.96
     Academy
    0.93
     Statistical
    0.92
     Civil
    0.91
     Petroleum
    0.91
    Activations Density 0.040%

    No Known Activations