© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 22690
    Prev
    Next
    INDEX
    Explanations

    phrases indicating passage of time over a period of years

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uala
    -0.77
    fy
    -0.72
    ulhu
    -0.70
    vu
    -0.69
    RIC
    -0.65
    Behind
    -0.65
    Boo
    -0.65
    Bio
    -0.64
    nces
    -0.64
    Bu
    -0.63
    POSITIVE LOGITS
     weekend
    0.99
     horizon
    0.88
     holidays
    0.87
     course
    0.84
     ensuing
    0.84
     span
    0.81
     whole
    0.80
    hang
    0.80
    arching
    0.79
     threshold
    0.79
    Activations Density 0.083%

    No Known Activations