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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 12536
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by places or objects

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    witch
    -0.91
    ifact
    -0.82
    ominated
    -0.80
    stall
    -0.70
    nesty
    -0.69
    isted
    -0.69
    inctions
    -0.68
    eteenth
    -0.68
    yip
    -0.67
    =\"
    -0.67
    POSITIVE LOGITS
     midst
    1.28
     pockets
    1.28
     pocket
    1.24
     vicinity
    1.24
     bloodstream
    1.16
     arsenal
    1.12
     own
    1.11
     backyard
    1.09
     stead
    1.07
     veins
    1.06
    Activations Density 0.148%

    No Known Activations