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. 12-RES-JB
    6. 15225
    Prev
    Next
    INDEX
    Explanations

    definite articles ('the', 'The') and specific locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    important historical or geographical entities and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    escription
    -0.87
    phies
    -0.82
    grades
    -0.80
    mares
    -0.79
    thood
    -0.76
    istries
    -0.76
    isson
    -0.74
    reau
    -0.74
    HP
    -0.73
    velt
    -0.72
    POSITIVE LOGITS
     birthplace
    1.56
     cradle
    1.25
     headquarters
    1.16
     capital
    1.15
     home
    1.11
     epic
    1.08
     gateway
    1.07
     hometown
    1.06
     stronghold
    1.04
     hub
    1.04
    Activations Density 0.152%

    No Known Activations