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. 3039
    Prev
    Next
    INDEX
    Explanations

    for and against arguments in a document

    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
    764
    +0.21
    0.7%
    184
    +0.19
    0.7%
    50
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.21
    0.01
    16
    +0.19
    0.04
    764
    +0.15
    0.03
    Negative Logits
    ьаж
    -0.94
    Географиясе
    -0.82
    jgl
    -0.79
    Aholisi
    -0.76
    <bos>
    -0.76
    Duración
    -0.76
    >//
    -0.76
    HasColumnName
    -0.75
    endwhile
    -0.74
    WindowConstants
    -0.73
    POSITIVE LOGITS
     reluct
    2.30
     affor
    2.25
     shenan
    2.23
     intersper
    2.22
     disagre
    2.19
     impra
    2.17
     encomp
    2.15
     increa
    2.12
     indestru
    2.10
     depic
    2.07
    Activations Density 0.198%

    No Known Activations