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. 688
    Prev
    Next
    INDEX
    Explanations

    descriptive details regarding the appearance and actions of 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
    1336
    +0.08
    0.2%
    1062
    +0.07
    0.2%
    1385
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1914
    +0.08
    0.05
    1446
    +0.07
    0.03
    1095
    +0.07
    0.02
    Negative Logits
     reluct
    -1.50
     gaily
    -1.47
     intersper
    -1.47
     impra
    -1.42
     shenan
    -1.40
     encomp
    -1.38
     maneu
    -1.37
     affor
    -1.35
     apprehen
    -1.34
     disagre
    -1.34
    POSITIVE LOGITS
     strict
    0.68
     rigid
    0.66
     precision
    0.64
     uniform
    0.64
     disciplined
    0.64
    uniform
    0.63
     discipline
    0.61
     straight
    0.59
    rigid
    0.58
    strict
    0.58
    Activations Density 0.761%

    No Known Activations