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. 18423
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of using something

    oai_token-act-pair · gpt-3.5-turbo

    possession and ownership expressions

    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
    uph
    -0.71
    ablishment
    -0.71
    ixon
    -0.69
    BALL
    -0.64
    yrinth
    -0.64
    nesty
    -0.62
    tsy
    -0.61
    jar
    -0.61
     Goes
    -0.60
    WAR
    -0.59
    POSITIVE LOGITS
     newfound
    1.30
     own
    1.19
     clout
    1.14
     expertise
    1.08
     discretion
    1.07
     fists
    1.03
     imagination
    1.00
     considerable
    0.99
     powers
    0.99
     leverage
    0.96
    Activations Density 0.121%

    No Known Activations