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. 8295
    Prev
    Next
    INDEX
    Explanations

    references to individuals

    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
    1671
    +0.16
    0.6%
    1984
    +0.14
    0.5%
    1691
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1671
    +0.16
    0.06
    1691
    +0.14
    0.05
    1984
    +0.13
    0.04
    Negative Logits
     répon
    -0.81
     malheureux
    -0.80
     accél
    -0.78
     soigne
    -0.77
     redé
    -0.75
     prét
    -0.75
     éc
    -0.75
     épar
    -0.74
     éprou
    -0.74
     attemp
    -0.74
    POSITIVE LOGITS
     someone
    0.96
     else
    0.91
    Someone
    0.90
     Someone
    0.89
     somebody
    0.87
    someone
    0.83
     who
    0.81
    Somebody
    0.78
    else
    0.72
     Somebody
    0.72
    Activations Density 0.119%

    No Known Activations