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. 3004
    Prev
    Next
    INDEX
    Explanations

    keywords related to causality and consequentialism

    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
    1013
    +0.14
    0.4%
    394
    +0.09
    0.3%
    2015
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1273
    +0.14
    0.03
    16
    +0.09
    0.07
    394
    +0.09
    0.04
    Negative Logits
     rafra
    -0.96
     Souha
    -0.94
     Mâ
    -0.81
     renfer
    -0.81
     Præ
    -0.81
     Autre
    -0.80
     Græ
    -0.79
     Châ
    -0.79
     Godt
    -0.78
     Câ
    -0.78
    POSITIVE LOGITS
     submitting
    0.73
     preparing
    0.71
     buying
    0.69
     việc
    0.69
     picking
    0.68
     collecting
    0.68
     designing
    0.68
     putting
    0.68
     creating
    0.68
     obtaining
    0.67
    Activations Density 0.629%

    No Known Activations