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. 13662
    Prev
    Next
    INDEX
    Explanations

    sentences related to family dynamics and communication issues

    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
    +0.11
    0.3%
    599
    +0.10
    0.3%
    1201
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.11
    0.06
    736
    +0.10
    0.08
    683
    +0.08
    0.07
    Negative Logits
     fta
    -1.43
     Abbé
    -1.41
     wien
    -1.41
     stockholm
    -1.40
     secon
    -1.40
     Simult
    -1.37
     emphat
    -1.37
     squa
    -1.36
     increa
    -1.34
     accla
    -1.33
    POSITIVE LOGITS
     mostly
    0.81
     modest
    0.81
     nothing
    0.76
     decent
    0.73
     minor
    0.73
     average
    0.71
     basic
    0.70
     fairly
    0.69
     mainly
    0.69
     maybe
    0.69
    Activations Density 1.182%

    No Known Activations