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. 10-RES-JB
    6. 24067
    Prev
    Next
    INDEX
    Explanations

    HTML tags and numerical values within the text

    oai_token-act-pair · gpt-3.5-turbo

    HTML or XML attribute-value pairs

    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
     limp
    -0.73
     pointing
    -0.72
     breed
    -0.71
     Reserv
    -0.69
     exchange
    -0.69
     betting
    -0.68
     Contra
    -0.68
     oriented
    -0.68
     Maher
    -0.68
     curled
    -0.66
    POSITIVE LOGITS
    true
    1.37
    False
    1.34
    false
    1.29
    ãĥ´ãĤ¡
    1.26
    True
    1.25
    ãĥīãĥ©ãĤ´ãĥ³
    1.24
    Abstract
    1.16
    0
    1.15
    yes
    1.14
    rss
    1.09
    Activations Density 0.021%

    No Known Activations