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. 8382
    Prev
    Next
    INDEX
    Explanations

    opinions or statements related to personal experiences and reflections

    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
    381
    +0.12
    0.4%
    1445
    +0.11
    0.3%
    184
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1533
    +0.12
    0.02
    1445
    +0.11
    0.06
    1877
    +0.10
    0.04
    Negative Logits
     swarovski
    -1.48
     ecru
    -1.41
     wikihow
    -1.38
     hairc
    -1.37
     embodi
    -1.30
     peppa
    -1.27
     aquarelle
    -1.23
     disreg
    -1.23
     cushi
    -1.22
    Noice
    -1.22
    POSITIVE LOGITS
     her
    0.89
     herself
    0.85
     she
    0.81
    حياتها
    0.77
    She
    0.72
    she
    0.71
    her
    0.70
    Her
    0.67
     She
    0.66
    herself
    0.65
    Activations Density 0.380%

    No Known Activations