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. 0-RES-JB
    6. 8423
    Prev
    Next
    INDEX
    Explanations

    personal belongings or possessions

    oai_token-act-pair · gpt-3.5-turbo

    references to personal matters or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oise
    -0.73
    tree
    -0.73
    cone
    -0.71
    osion
    -0.70
    rats
    -0.67
    swick
    -0.67
    rose
    -0.66
    lake
    -0.66
    casts
    -0.65
    rophe
    -0.65
    POSITIVE LOGITS
     personal
    3.47
    personal
    2.70
    Personal
    2.56
     Personal
    2.47
     personally
    2.03
     personalized
    1.72
     private
    1.49
     PERSON
    1.44
     interpersonal
    1.29
     intimate
    1.24
    Activations Density 0.018%

    No Known Activations