© 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. 10-RES-JB
    11. 24025
    Prev
    Next
    INDEX
    Explanations

    dates or time-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "this" in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ickets
    -0.74
    rics
    -0.69
    ular
    -0.67
    tery
    -0.64
    gans
    -0.64
    stones
    -0.64
    sers
    -0.61
    cases
    -0.61
    icons
    -0.60
    riott
    -0.60
    POSITIVE LOGITS
     week
    1.58
     morning
    1.53
     afternoon
    1.50
     weekend
    1.49
     month
    1.39
     evening
    1.30
     summer
    1.28
     year
    1.18
     past
    1.18
     spring
    1.17
    Activations Density 0.078%

    No Known Activations