Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23019
    Prev
    Next
    INDEX
    Explanations

    keywords related to the day of the week "Thursday"

    oai_token-act-pair · gpt-3.5-turbo

    references to the day Thursday

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chest
    -0.86
    ership
    -0.84
    pend
    -0.82
    respons
    -0.81
    sym
    -0.80
    Ñĭ
    -0.79
    acerb
    -0.72
    colour
    -0.71
    ates
    -0.68
    ate
    -0.66
    POSITIVE LOGITS
     morning
    1.43
     afternoon
    1.40
     evening
    1.28
     night
    1.25
     Night
    1.13
     mornings
    1.07
     evenings
    1.05
     nights
    1.04
    rd
    0.94
    night
    0.86
    Activations Density 0.024%

    No Known Activations