Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15870
    Prev
    Next
    INDEX
    Explanations

    ranges or numerical values expressed as ratios

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating approximate numerical ranges

    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
    ModLoader
    -0.96
    åŃIJ
    -0.72
    ACTED
    -0.71
    ById
    -0.69
    jay
    -0.68
    ãĤ´ãĥ³
    -0.66
    çķ
    -0.65
    eries
    -0.63
    NetMessage
    -0.63
    ÑĮ
    -0.62
    POSITIVE LOGITS
     60
    1.35
     80
    1.31
     120
    1.30
     70
    1.29
     90
    1.24
     150
    1.24
     100
    1.23
     40
    1.18
     50
    1.17
     75
    1.17
    Activations Density 0.050%

    No Known Activations