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. 13599
    Prev
    Next
    INDEX
    Explanations

    names of places or names of people

    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
    1896
    +0.15
    0.6%
    381
    +0.15
    0.6%
    1177
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.15
    0.07
    1896
    +0.15
    0.05
    144
    +0.14
    0.05
    Negative Logits
    <bos>
    -1.30
     그것
    -0.79
     나는
    -0.73
     for
    -0.71
     just
    -0.71
     in
    -0.70
     자신의
    -0.69
     at
    -0.69
     책
    -0.68
     within
    -0.68
    POSITIVE LOGITS
     embra
    1.81
     effe
    1.80
     dispen
    1.80
     alkoh
    1.76
     abnorm
    1.72
     pessi
    1.71
     bett
    1.69
     kram
    1.69
     simplif
    1.68
     wien
    1.68
    Activations Density 0.297%

    No Known Activations