© 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. 11-RES-JB
    11. 1916
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific research and study

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the word "the" in various contexts, suggesting a focus on specific subjects or elements in a discussion

    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
    Advertisement
    -0.88
    illion
    -0.81
    Sound
    -0.77
    Planet
    -0.76
    whatever
    -0.76
    ebook
    -0.75
     Deals
    -0.75
    illions
    -0.74
    cean
    -0.74
     Anyone
    -0.74
    POSITIVE LOGITS
     presence
    1.33
     occurrence
    1.26
     latter
    1.20
     absence
    1.19
     prevalence
    1.19
     foregoing
    1.19
     efficacy
    1.17
    oret
    1.17
     hypothesis
    1.17
     magnitude
    1.16
    Activations Density 0.246%

    No Known Activations