© 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. 7-RES-JB
    11. 2695
    Prev
    Next
    INDEX
    Explanations

    phrases related to reports or official statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the word "states."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.78
    iffe
    -0.70
     Carbuncle
    -0.65
     suscept
    -0.62
     noses
    -0.62
     Torn
    -0.60
     rains
    -0.60
     People
    -0.59
    ãĤ¼
    -0.59
    isoft
    -0.58
    POSITIVE LOGITS
     unequivocally
    0.91
     bluntly
    0.78
     emphatically
    0.77
    manship
    0.75
    rooms
    0.74
     plainly
    0.73
    ide
    0.71
    told
    0.71
    reth
    0.71
     boldly
    0.70
    Activations Density 0.016%

    No Known Activations