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. 9-RES-JB
    6. 9333
    Prev
    Next
    INDEX
    Explanations

    clothing items and activities related to sports

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to working-class struggles and related socio-economic themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ambrose
    -0.71
     wiret
    -0.66
     numerical
    -0.65
     Hector
    -0.65
     infall
    -0.64
     deposition
    -0.64
     Vall
    -0.63
     Unicode
    -0.63
     UD
    -0.62
     DHCP
    -0.61
    POSITIVE LOGITS
    loving
    1.35
    related
    1.22
    indust
    1.21
    mad
    1.21
    hun
    1.18
    grounds
    1.17
    brother
    1.17
    themed
    1.15
    hung
    1.15
    lot
    1.12
    Activations Density 0.099%

    No Known Activations