© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 22764
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and military actions involving the United States

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     STATS
    -0.85
    */(
    -0.83
    ĵĺ
    -0.69
     "$:/
    -0.64
    Ont
    -0.64
    bred
    -0.63
     Manitoba
    -0.61
    bleacher
    -0.60
     shave
    -0.60
     shaved
    -0.59
    POSITIVE LOGITS
     embassy
    0.88
    istani
    0.85
     Embassy
    0.85
    ierra
    0.85
    wan
    0.83
    gt
    0.83
    eal
    0.82
    AAF
    0.80
    ugg
    0.78
    oday
    0.76
    Activations Density 0.040%

    No Known Activations