© 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. 3138
    Prev
    Next
    INDEX
    Explanations

    specific years

    oai_token-act-pair · gpt-3.5-turbo

    references to the year 2002

    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
    ledged
    -0.71
    hma
    -0.71
     unch
    -0.70
    upp
    -0.69
    imated
    -0.69
    utters
    -0.68
    stakes
    -0.66
    lying
    -0.64
    awed
    -0.64
    attled
    -0.63
    POSITIVE LOGITS
    2002
    0.87
    1982
    0.83
    å¹
    0.81
    2003
    0.80
     2002
    0.79
    2001
    0.79
     2003
    0.79
    2004
    0.77
    -'
    0.77
    1998
    0.77
    Activations Density 0.011%

    No Known Activations