© 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. 21819
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges and events happening in specific locations

    oai_token-act-pair · gpt-3.5-turbo

    completely empty segments or breaks in the text

    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
     himself
    -0.83
     herself
    -0.80
    tein
    -0.78
     oneself
    -0.75
     themselves
    -0.68
    nikov
    -0.67
     Himself
    -0.65
    stroke
    -0.64
    ensor
    -0.63
    opped
    -0.63
    POSITIVE LOGITS
     selves
    1.35
     ancestors
    1.13
     ourselves
    1.11
     partners
    1.08
     counterparts
    1.07
     brethren
    1.02
     cousins
    0.96
     asses
    0.87
     heroes
    0.87
     motto
    0.85
    Activations Density 0.261%

    No Known Activations