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. 8390
    Prev
    Next
    INDEX
    Explanations

    specific locations

    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
    421
    +0.11
    0.4%
    489
    +0.11
    0.4%
    1937
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1081
    +0.11
    0.04
    814
    +0.11
    0.03
    1937
    +0.11
    0.04
    Negative Logits
     NOO
    -0.86
     ?...
    -0.84
     desir
    -0.83
     ??????
    -0.82
     !?
    -0.81
     nece
    -0.79
     aen
    -0.77
     fuf
    -0.76
     effe
    -0.76
     bandung
    -0.76
    POSITIVE LOGITS
    there
    0.81
     there
    0.80
     THERE
    0.74
    THERE
    0.68
     There
    0.67
    There
    0.64
     článek
    0.53
    SharedDtor
    0.52
    allible
    0.51
    徨
    0.51
    Activations Density 0.107%

    No Known Activations