© 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. 1-RES-JB
    11. 9432
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "decade"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "decade" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    swick
    -0.78
     Answer
    -0.74
     Pegasus
    -0.67
    Reviewer
    -0.66
     Rush
    -0.64
     Panther
    -0.63
     Shin
    -0.62
    Pros
    -0.60
     Abyssal
    -0.60
    culosis
    -0.59
    POSITIVE LOGITS
    ibel
    1.03
    orate
    0.98
    oded
    0.96
    EMBER
    0.93
    ryption
    0.92
    rypted
    0.91
    theless
    0.90
    isions
    0.89
    ision
    0.87
    rypt
    0.82
    Activations Density 0.007%

    No Known Activations