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. 541
    Prev
    Next
    INDEX
    Explanations

    states about statistics and research data

    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
    453
    +0.18
    0.5%
    1978
    +0.10
    0.3%
    184
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.18
    0.06
    1377
    +0.10
    0.03
    1919
    +0.08
    0.05
    Negative Logits
     utop
    -0.80
    kháu
    -0.78
     Italijani
    -0.76
     Ause
    -0.76
    OCCURRED
    -0.76
    jgl
    -0.74
    onViewCreated
    -0.72
    contentLoaded
    -0.72
    Élet
    -0.71
     <",
    -0.71
    POSITIVE LOGITS
     reluct
    1.02
     encomp
    0.99
     strick
    0.98
     guarante
    0.98
     shenan
    0.98
     disagre
    0.96
     withal
    0.94
     increa
    0.93
     fuf
    0.92
     affor
    0.92
    Activations Density 0.420%

    No Known Activations