© 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. 10-RES-JB
    11. 11406
    Prev
    Next
    INDEX
    Explanations

    speculative phrases about the future

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various contexts, indicating a focus on significant or notable subjects

    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
    lement
    -0.72
    aco
    -0.66
    alone
    -0.63
    ousy
    -0.62
    folk
    -0.62
    arson
    -0.60
    tel
    -0.59
    thood
    -0.57
    bots
    -0.57
    bourg
    -0.56
    POSITIVE LOGITS
     verge
    1.62
     brink
    1.48
     lookout
    1.30
     forefront
    1.16
     chopping
    1.04
     periphery
    0.99
     sidelines
    0.98
     edge
    0.98
     heels
    0.97
     precip
    0.96
    Activations Density 0.066%

    No Known Activations