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. 1489
    Prev
    Next
    INDEX
    Explanations

    phrases describing possession or association with an entity

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms and contractions

    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
    rg
    -0.73
    sson
    -0.72
    roup
    -0.70
    INST
    -0.70
    stad
    -0.68
    Alert
    -0.67
    tsy
    -0.67
    itcher
    -0.64
    ISC
    -0.63
    owitz
    -0.63
    POSITIVE LOGITS
     sake
    1.03
     finest
    0.92
     Greatest
    0.89
     biggest
    0.88
    ELF
    0.85
     greatest
    0.84
     hars
    0.82
     namesake
    0.81
     maiden
    0.78
     newest
    0.77
    Activations Density 0.129%

    No Known Activations