© 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. 11-RES-JB
    11. 10274
    Prev
    Next
    INDEX
    Explanations

    dates related to specific weekdays, primarily Wednesdays

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days of the week

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ordes
    -0.64
    allow
    -0.64
    sbm
    -0.63
    avorite
    -0.63
    onne
    -0.62
    userc
    -0.61
    onet
    -0.58
    åĬ
    -0.58
    ij士
    -0.57
     spoiler
    -0.56
    POSITIVE LOGITS
     evenings
    1.25
     nights
    1.24
     mornings
    1.22
     October
    1.20
     afternoon
    1.17
     September
    1.15
     evening
    1.14
     December
    1.13
     February
    1.13
     November
    1.13
    Activations Density 0.068%

    No Known Activations