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. 8400
    Prev
    Next
    INDEX
    Explanations

    phrases related to judgement and evaluation

    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
    +0.10
    0.3%
    236
    +0.07
    0.2%
    2025
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1470
    +0.10
    0.04
    1827
    +0.07
    0.04
    208
    +0.07
    0.05
    Negative Logits
     unlaw
    -1.42
     guarante
    -1.27
     volunte
    -1.26
     panama
    -1.26
     swarovski
    -1.25
     encomp
    -1.24
     affor
    -1.24
     increa
    -1.23
     impra
    -1.22
     strick
    -1.21
    POSITIVE LOGITS
     choosing
    0.68
     leaving
    0.62
     bringing
    0.61
     assuming
    0.59
     allowing
    0.59
     considering
    0.59
     sending
    0.58
     letting
    0.58
     putting
    0.57
     having
    0.57
    Activations Density 0.344%

    No Known Activations