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. 13538
    Prev
    Next
    INDEX
    Explanations

    terms related to specific goals or intentions

    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
    2025
    +0.09
    0.3%
    596
    +0.08
    0.2%
    2041
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2041
    +0.09
    0.05
    596
    +0.08
    0.04
    1992
    +0.08
    0.03
    Negative Logits
     kram
    -0.81
     Okt
    -0.79
     naer
    -0.72
     saad
    -0.72
     gij
    -0.69
     kug
    -0.68
     osal
    -0.68
     territo
    -0.68
     uhr
    -0.68
     priva
    -0.67
    POSITIVE LOGITS
     goal
    0.72
     Goal
    0.58
    goal
    0.58
     aim
    0.55
    Goal
    0.54
     objective
    0.53
     OBJECTIVE
    0.52
     déclarations
    0.52
     objectifs
    0.52
     sièges
    0.51
    Activations Density 0.172%

    No Known Activations