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. 15676
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    1741
    +0.14
    0.4%
    382
    +0.14
    0.4%
    1445
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.14
    0.04
    10
    +0.14
    0.04
    382
    +0.12
    0.04
    Negative Logits
     shenan
    -1.32
     intersper
    -1.28
     philanth
    -1.19
     disreg
    -1.16
     encomp
    -1.16
     indestru
    -1.12
     Intere
    -1.10
     resear
    -1.09
     OGS
    -1.08
     depic
    -1.08
    POSITIVE LOGITS
    0
    0.58
    5
    0.55
    openqa
    0.55
    8
    0.52
     sostanze
    0.52
    Kết
    0.51
    feras
    0.51
    9
    0.51
    6
    0.51
    4
    0.50
    Activations Density 0.079%

    No Known Activations