© 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. 0-RES-JB
    11. 533
    Prev
    Next
    INDEX
    Explanations

    timestamps in GMT format

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time zones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rie
    -0.67
    requ
    -0.65
    evin
    -0.65
    upe
    -0.64
     Daniels
    -0.63
     dis
    -0.61
     cour
    -0.61
    orah
    -0.60
     Crow
    -0.60
     pra
    -0.60
    POSITIVE LOGITS
     GMT
    4.22
    GMT
    2.70
     BST
    2.46
     UTC
    1.99
     CET
    1.69
     PDT
    1.52
     EDT
    1.49
    UTC
    1.48
     PST
    1.39
     CST
    1.36
    Activations Density 0.017%

    No Known Activations