© 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. 11-RES-JB
    11. 10218
    Prev
    Next
    INDEX
    Explanations

    mentions or references to specific individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    repeated special characters or symbols in a text

    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
     envy
    -0.74
     hindsight
    -0.73
     Belg
    -0.67
     Guinness
    -0.67
     obfusc
    -0.65
     extrap
    -0.65
     shack
    -0.65
     Lag
    -0.64
     disappoint
    -0.63
     decomp
    -0.62
    POSITIVE LOGITS
    ı
    1.58
    ¬
    1.42
    º
    1.41
    ª
    1.40
    Į
    1.38
    Ń
    1.37
    ²
    1.35
    £
    1.35
    Ĵ
    1.31
    IJ
    1.31
    Activations Density 0.149%

    No Known Activations