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. 3104
    Prev
    Next
    INDEX
    Explanations

    starting and ending phrases in texts

    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
    159
    +0.09
    0.3%
    1503
    +0.07
    0.2%
    1822
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1497
    +0.09
    0.03
    1030
    +0.07
    0.02
    1309
    +0.07
    0.02
    Negative Logits
     ftu
    -0.87
     fta
    -0.86
     »>
    -0.85
     thut
    -0.83
    :,,
    -0.83
    «<
    -0.80
     fince
    -0.79
     fte
    -0.79
     ftre
    -0.79
     Abbé
    -0.77
    POSITIVE LOGITS
     currently
    0.92
     immediate
    0.91
     presently
    0.86
     current
    0.83
    current
    0.75
     today
    0.73
     interim
    0.73
     Currently
    0.72
    Currently
    0.72
    immediate
    0.72
    Activations Density 0.345%

    No Known Activations