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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15232
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns related to ownership

    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
    Downloadha
    -0.76
    ogly
    -0.70
    vati
    -0.68
    pole
    -0.67
    ctr
    -0.65
    threat
    -0.63
    weather
    -0.63
    ç
    -0.61
    legram
    -0.60
    ļéĨĴ
    -0.60
    POSITIVE LOGITS
     choosing
    1.65
     own
    1.38
     choice
    1.28
     Own
    1.00
     liking
    0.99
     OWN
    0.96
     imagination
    0.96
     invention
    0.91
     namesake
    0.90
     utmost
    0.86
    Activations Density 0.098%

    No Known Activations