Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 4
    Prev
    Next
    INDEX
    Explanations

    words related to locations or proper nouns related to buildings/places

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    966
    +0.10
    0.4%
    50
    +0.10
    0.4%
    528
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.05
    214
    +0.10
    0.03
    283
    +0.07
    0.01
    Negative Logits
    <bos>
    -1.05
    lenmiş
    -0.74
    /*++
    -0.74
    lenir
    -0.67
     would
    -0.67
    <?
    
    -0.66
     became
    -0.65
     keep
    -0.65
    public
    -0.65
     accept
    -0.65
    POSITIVE LOGITS
    le
    2.00
     mef
    1.74
     effe
    1.71
     illi
    1.68
     sovere
    1.68
     Intere
    1.67
     socie
    1.65
     maneu
    1.64
     véhic
    1.64
     erec
    1.63
    Activations Density 0.202%

    No Known Activations