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 · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15095
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions or interactions

    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
    1356
    +0.09
    0.3%
    1038
    +0.08
    0.2%
    1103
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.09
    0.03
    1356
    +0.08
    0.03
    1608
    +0.08
    0.02
    Negative Logits
     quitted
    -0.98
     gaily
    -0.96
     apprehen
    -0.95
     maneu
    -0.95
     disagre
    -0.94
     berea
    -0.93
     depic
    -0.92
     encomp
    -0.90
     thut
    -0.90
     shewn
    -0.89
    POSITIVE LOGITS
    batore
    0.56
     Milán
    0.53
     gelo
    0.52
     sodio
    0.51
     poliuret
    0.51
     manuten
    0.51
    Enf
    0.50
    spaceBetween
    0.50
     Holanda
    0.48
     Suecia
    0.48
    Activations Density 0.455%

    No Known Activations