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. 8312
    Prev
    Next
    INDEX
    Explanations

    references to specific titles of old-school isometric RPGs

    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
    1842
    +0.15
    0.5%
    394
    +0.14
    0.4%
    1343
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1314
    +0.15
    0.06
    1842
    +0.14
    0.05
    227
    +0.13
    0.06
    Negative Logits
     direct
    -0.62
     widać
    -0.60
     протяжении
    -0.59
     to
    -0.59
    jaardag
    -0.59
     '
    -0.57
     onto
    -0.57
     hard
    -0.57
    处于
    -0.57
     fresh
    -0.57
    POSITIVE LOGITS
     mef
    1.71
     fta
    1.66
     immen
    1.61
     ftu
    1.61
     nece
    1.58
     embra
    1.57
     milano
    1.57
     hcm
    1.57
     pessi
    1.56
     fup
    1.56
    Activations Density 0.445%

    No Known Activations