© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 5205
    Prev
    Next
    INDEX
    Explanations

    organizations and roles of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or institutions, particularly in a formal context

    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
    ¥µ
    -0.62
    animate
    -0.62
    Pg
    -0.61
    ãĥİ
    -0.58
    âĶģ
    -0.58
     Seym
    -0.57
    Sche
    -0.57
    Loading
    -0.57
    ãģį
    -0.56
    Ö
    -0.56
    POSITIVE LOGITS
     criticised
    0.96
     discusses
    0.96
     apologised
    0.93
     testified
    0.91
     congratulated
    0.91
     wrote
    0.90
     warns
    0.89
     cautioned
    0.87
     told
    0.86
     urged
    0.86
    Activations Density 0.511%

    No Known Activations