© 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. 8-RES-JB
    11. 1246
    Prev
    Next
    INDEX
    Explanations

    references to specific names or entities, particularly focusing on names starting with 'Du'

    oai_token-act-pair · gpt-3.5-turbo

    the word "uch" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eaves
    -0.65
     contrace
    -0.64
     Wass
    -0.62
     diminishing
    -0.62
     cir
    -0.60
     parting
    -0.60
     stripping
    -0.60
    ences
    -0.60
     primed
    -0.60
     tampering
    -0.58
    POSITIVE LOGITS
    icago
    1.24
    anan
    0.89
    arist
    0.82
    onne
    0.81
    arest
    0.80
    ocobo
    0.76
    annel
    0.75
    ampion
    0.73
    ynski
    0.72
    rone
    0.71
    Activations Density 0.017%

    No Known Activations