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. 15933
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progress or advancement in a continuous effort

    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
    598
    +0.07
    0.2%
    838
    +0.07
    0.2%
    9
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1312
    +0.07
    0.04
    838
    +0.07
    0.04
    1087
    +0.07
    0.03
    Negative Logits
     Keny
    -0.77
     Manufact
    -0.75
     Intere
    -0.71
     increa
    -0.71
     wherea
    -0.71
     reluct
    -0.70
     strick
    -0.69
     exorbit
    -0.69
     traktor
    -0.69
     moza
    -0.68
    POSITIVE LOGITS
     still
    0.65
    still
    0.57
    <bos>
    0.57
    Still
    0.54
     Still
    0.52
     room
    0.52
     tasks
    0.51
     noch
    0.50
     ancora
    0.48
     to
    0.48
    Activations Density 0.169%

    No Known Activations