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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 4426
    Prev
    Next
    INDEX
    Explanations

    phrases related to working hard or putting in effort

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.23
    0.8%
    1839
    +0.10
    0.4%
    297
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.23
    0.05
    1992
    +0.10
    0.04
    297
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.46
     acquaint
    -0.70
     inaugurate
    -0.68
     rejoin
    -0.60
     introduce
    -0.58
     reunite
    -0.58
     transact
    -0.57
     abolish
    -0.57
     disbur
    -0.57
     preside
    -0.56
    POSITIVE LOGITS
     bandung
    1.32
     paradiso
    1.25
    gruntled
    1.18
     kebaya
    1.13
     Minang
    1.13
     jaya
    1.11
     riva
    1.10
     riviera
    1.10
     montagna
    1.08
     palio
    1.07
    Activations Density 0.603%

    No Known Activations