© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2460
    Prev
    Next
    INDEX
    Explanations

    mentions of footwear and related experiences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1385
    +0.15
    0.5%
    1369
    +0.10
    0.3%
    736
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.15
    0.05
    1369
    +0.10
    0.02
    226
    +0.10
    0.02
    Negative Logits
     alkoh
    -1.11
     praktik
    -1.04
     reger
    -1.03
     ideolog
    -1.02
     meras
    -0.97
     utop
    -0.96
     uhr
    -0.95
     liev
    -0.95
     dises
    -0.94
     lemp
    -0.94
    POSITIVE LOGITS
     footwear
    0.72
     conftest
    0.71
     fameux
    0.70
     shoes
    0.69
     worn
    0.61
     ferric
    0.59
     avenger
    0.59
     merveilleux
    0.57
     slippers
    0.57
     hydrogel
    0.57
    Activations Density 0.247%

    No Known Activations