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. 11-RES-JB
    6. 8245
    Prev
    Next
    INDEX
    Explanations

    personal pronouns signifying possession or association

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and references to individual players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AppData
    -0.73
     Cheong
    -0.72
    ulhu
    -0.72
    hari
    -0.72
    INTON
    -0.71
    hyde
    -0.70
    leanor
    -0.69
     Lyndon
    -0.69
     Dorothy
    -0.69
    uminati
    -0.68
    POSITIVE LOGITS
     teammates
    1.25
     versatility
    1.15
     teammate
    1.12
     antics
    1.09
     absence
    1.07
     prowess
    1.05
     penchant
    1.05
     athleticism
    1.04
     performances
    1.03
     career
    1.02
    Activations Density 0.152%

    No Known Activations