© 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. 8-RES-JB
    11. 5042
    Prev
    Next
    INDEX
    Explanations

    specific time formats with emphasis on PM times

    oai_token-act-pair · gpt-3.5-turbo

    specific time-related terms or formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orously
    -0.69
    abul
    -0.67
    é¾
    -0.65
    ãĤ·ãĥ£
    -0.65
    oys
    -0.65
    taboola
    -0.64
    forums
    -0.64
    enn
    -0.62
    æ°
    -0.61
    ederation
    -0.61
    POSITIVE LOGITS
     1
    1.51
     2
    1.45
     0
    1.38
     3
    1.37
     4
    1.23
     5
    1.17
     6
    1.11
     7
    1.04
     ½
    1.02
     9
    0.94
    Activations Density 0.141%

    No Known Activations