Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14891
    Prev
    Next
    INDEX
    Explanations

    dialogue quotations

    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
    2019
    +0.32
    1.1%
    381
    +0.24
    0.8%
    924
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.32
    0.05
    2019
    +0.24
    0.04
    545
    +0.11
    0.04
    Negative Logits
    FTFY
    -0.71
    Whoo
    -0.69
    Ehh
    -0.68
    Hahahahaha
    -0.66
    Fuckin
    -0.61
    Hahahaha
    -0.60
    Ohhhh
    -0.58
    Wtf
    -0.58
    Aah
    -0.58
    Lmfao
    -0.57
    POSITIVE LOGITS
     héro
    0.73
     provisoire
    0.73
     confé
    0.72
     ambassade
    0.70
     cartier
    0.70
     ovunque
    0.68
     écou
    0.67
     vété
    0.66
     accanto
    0.65
     étrang
    0.65
    Activations Density 0.120%

    No Known Activations