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. 9555
    Prev
    Next
    INDEX
    Explanations

    pronouns 'his' or 'His' in the context of possessive use or relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual's possessions or actions

    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
    ocument
    -0.92
    IVERS
    -0.73
    izabeth
    -0.73
    ibaba
    -0.71
    agara
    -0.69
    otin
    -0.67
    Downloadha
    -0.66
    Trend
    -0.66
    skirts
    -0.66
    anguage
    -0.65
    POSITIVE LOGITS
    panic
    1.50
     wife
    1.40
     own
    1.30
     Majesty
    1.29
    sing
    1.27
     Emin
    1.14
    pan
    1.09
     father
    1.05
     girlfriend
    1.03
    sed
    1.02
    Activations Density 0.270%

    No Known Activations