© 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. 4-RES-JB
    11. 23672
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, particularly focusing on places or organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to organizations and entities

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

    No Comments

    Negative Logits
    htar
    -0.89
    iper
    -0.86
    hene
    -0.82
    icka
    -0.80
    yon
    -0.79
    culosis
    -0.75
    etting
    -0.75
    iator
    -0.73
    inen
    -0.73
    kens
    -0.72
    POSITIVE LOGITS
     Advice
    0.81
    é¾įå¥ij士
    0.81
     Consumer
    0.80
     Desk
    0.75
     Mouse
    0.74
    aples
    0.73
     Scientific
    0.73
     Staples
    0.72
     Warranty
    0.72
     Surve
    0.71
    Activations Density 0.031%

    No Known Activations