© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 12728
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by body parts or personal items

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating ownership or belonging

    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
    witch
    -0.81
    bender
    -0.70
    ominated
    -0.68
    ifact
    -0.68
    hyde
    -0.67
    inctions
    -0.67
    nesty
    -0.66
    eenth
    -0.66
    eers
    -0.66
    otin
    -0.64
    POSITIVE LOGITS
     pockets
    1.24
     pocket
    1.24
     midst
    1.17
     veins
    1.15
     bloodstream
    1.13
     own
    1.13
     backyard
    1.10
     inbox
    1.10
     arsenal
    1.10
     vicinity
    1.08
    Activations Density 0.092%

    No Known Activations