© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14641
    Prev
    Next
    INDEX
    Explanations

    phrases referring to technological advancements from the late 20th century

    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
    1343
    +0.22
    0.8%
    453
    +0.19
    0.7%
    764
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.22
    0.06
    764
    +0.19
    0.04
    856
    +0.15
    0.04
    Negative Logits
     ftu
    -1.73
     disagre
    -1.72
     fta
    -1.70
     inev
    -1.69
     thut
    -1.68
     reluct
    -1.66
     Juf
    -1.63
     Mlle
    -1.63
     shenan
    -1.61
     increa
    -1.59
    POSITIVE LOGITS
    GraphicsUnit
    0.56
    <bos>
    0.54
    Portály
    0.54
    ֽ
    0.54
     MessageBoxIcon
    0.53
    <eos>
    0.53
     Baillargeon
    0.52
    .
    0.52
     ¡
    0.50
     AllMovie
    0.50
    Activations Density 0.408%

    No Known Activations