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. 15761
    Prev
    Next
    INDEX
    Explanations

    terms related to networks and operations

    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
    1150
    +0.11
    0.3%
    1343
    +0.11
    0.3%
    394
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.11
    0.09
    1819
    +0.11
    0.07
    1082
    +0.11
    0.05
    Negative Logits
    istible
    -0.71
     незавершена
    -0.65
    <bos>
    -0.63
    copg
    -0.62
    weile
    -0.61
    istisches
    -0.60
    ureusement
    -0.60
    TargetException
    -0.58
    curacies
    -0.57
    ­
    -0.56
    POSITIVE LOGITS
     shenan
    1.86
     ineffec
    1.75
     unspeak
    1.73
     apprehen
    1.71
     maneu
    1.69
     disagre
    1.69
     depic
    1.69
     reluct
    1.69
     gaily
    1.65
     increa
    1.63
    Activations Density 0.744%

    No Known Activations