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. 6-RES-JB
    6. 40
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Detroit."

    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
    1068
    +0.19
    1.1%
    687
    +0.18
    1.0%
    313
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.19
    0.04
    1677
    +0.18
    0.03
    478
    +0.16
    0.02
    Negative Logits
    <bos>
    -0.87
     intersper
    -0.82
     Lorsqu
    -0.76
     encomp
    -0.72
     reconno
    -0.69
     apprehen
    -0.66
     gild
    -0.66
     Jusqu
    -0.65
     Pense
    -0.65
     unve
    -0.64
    POSITIVE LOGITS
     Detroit
    1.02
    Detroit
    0.97
     DETROIT
    0.90
    detroit
    0.90
     Det
    0.87
    ROIT
    0.75
     PLWABN
    0.75
    Det
    0.72
     det
    0.71
     DET
    0.67
    Activations Density 0.619%

    No Known Activations