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. 1295
    Prev
    Next
    INDEX
    Explanations

    descriptions of baking recipes and ingredients

    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
    876
    +0.23
    0.8%
    736
    +0.13
    0.4%
    519
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.23
    0.07
    519
    +0.13
    0.04
    876
    +0.12
    -0.01
    Negative Logits
     Jurist
    -0.95
     monaster
    -0.83
     Hauptmann
    -0.75
     kemer
    -0.75
     Rektor
    -0.72
     cittad
    -0.72
     Kriminal
    -0.71
     Bundestag
    -0.69
     Presidencia
    -0.69
     Conferencia
    -0.68
    POSITIVE LOGITS
     ftu
    1.44
     increa
    1.33
     fta
    1.31
     purcha
    1.28
     guarante
    1.28
     affor
    1.25
     embodi
    1.25
     poff
    1.23
     disagre
    1.21
     ftre
    1.19
    Activations Density 0.356%

    No Known Activations