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. 8-RES-JB
    6. 3804
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive pronouns followed by a possessive noun phrase

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and their usage in relation to people and things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eers
    -0.88
    wrap
    -0.77
    inctions
    -0.74
    Downloadha
    -0.72
    daq
    -0.70
     Barron
    -0.70
    cookie
    -0.70
    eus
    -0.69
    eer
    -0.68
    verb
    -0.66
    POSITIVE LOGITS
     own
    1.47
     predecessors
    1.19
     respective
    1.06
     choosing
    1.04
     peers
    1.02
     newfound
    1.01
     predecessor
    1.00
     beloved
    0.99
     namesake
    0.98
     surroundings
    0.97
    Activations Density 0.215%

    No Known Activations