© 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. 6498
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and quantity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate quantities, specifically those expressing amounts marginally above or below a certain threshold

    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
    illary
    -0.74
    alogy
    -0.72
    alam
    -0.70
    antine
    -0.68
    uity
    -0.66
    hess
    -0.66
    Ô
    -0.64
    olis
    -0.63
     Citation
    -0.63
    oves
    -0.63
    POSITIVE LOGITS
     half
    0.77
     halfway
    0.72
    whelming
    0.71
    whel
    0.69
    vernment
    0.69
     ½
    0.66
     powering
    0.66
    loading
    0.65
    capacity
    0.63
     shy
    0.63
    Activations Density 0.031%

    No Known Activations