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. 8300
    Prev
    Next
    INDEX
    Explanations

    programming code snippets concerning a specific class or object constructor

    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
    227
    +0.18
    0.6%
    453
    +0.17
    0.5%
    16
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.18
    0.03
    876
    +0.17
    -0.00
    334
    +0.15
    0.02
    Negative Logits
     unlaw
    -0.93
     McLaugh
    -0.89
     endeavouring
    -0.86
     assailed
    -0.75
     idleness
    -0.74
     vainly
    -0.74
     impelled
    -0.74
     negroes
    -0.73
     endeav
    -0.72
     seamen
    -0.71
    POSITIVE LOGITS
     espé
    1.65
     télécharge
    1.59
     vété
    1.55
     célé
    1.47
     confé
    1.46
     nôtre
    1.44
     noël
    1.38
     Chinois
    1.38
     actualité
    1.37
     récon
    1.36
    Activations Density 0.073%

    No Known Activations