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. 13553
    Prev
    Next
    INDEX
    Explanations

    information related to computer hardware specifications, specifically focusing on bit capacities and memory storage sizes

    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
    1691
    +0.13
    0.5%
    1407
    +0.12
    0.4%
    1328
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    667
    +0.13
    0.04
    1437
    +0.12
    0.03
    2036
    +0.11
    0.03
    Negative Logits
    Ży
    -0.78
    prägt
    -0.58
     solemnity
    -0.55
    arroz
    -0.54
     doña
    -0.54
    Fordítás
    -0.53
     ruinas
    -0.52
    Wię
    -0.52
     clergyman
    -0.52
    Kiedy
    -0.51
    POSITIVE LOGITS
     meis
    1.24
     kram
    1.20
     ohr
    1.13
     aen
    1.13
     hina
    1.10
     zyn
    1.08
     kac
    1.07
     lele
    1.06
     fei
    1.04
     ert
    1.03
    Activations Density 0.112%

    No Known Activations