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. 13554
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and criminal actions

    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
    1042
    +0.09
    0.2%
    604
    +0.08
    0.2%
    453
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1395
    +0.09
    0.04
    1309
    +0.08
    0.03
    1128
    +0.08
    0.06
    Negative Logits
     aen
    -1.32
     increa
    -1.32
     desir
    -1.25
     thut
    -1.24
     fluo
    -1.22
     effe
    -1.21
     inev
    -1.20
     guarante
    -1.20
     nutella
    -1.18
     impra
    -1.17
    POSITIVE LOGITS
     disciplinary
    0.74
     CreateTagHelper
    0.61
     suspension
    0.61
    disciplinary
    0.57
     misconduct
    0.56
     punishment
    0.54
     suspended
    0.54
     impeachment
    0.54
    DeleteBehavior
    0.53
     للاسماء
    0.52
    Activations Density 0.734%

    No Known Activations