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. 5345
    Prev
    Next
    INDEX
    Explanations

    references to specific names or terms related to hair styling and beauty services

    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
    1810
    +0.18
    1.0%
    1404
    +0.15
    0.8%
    1387
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.18
    0.04
    1097
    +0.15
    0.06
    1343
    +0.15
    0.07
    Negative Logits
    <bos>
    -0.77
     Agnew
    -0.70
     Searle
    -0.67
    Demografia
    -0.62
    Giao
    -0.57
    PropertyGroup
    -0.55
    Referințe
    -0.54
    marginHorizontal
    -0.54
    Vezi
    -0.53
    DataContract
    -0.53
    POSITIVE LOGITS
     Whit
    1.31
    Whit
    1.20
     WHIT
    1.16
     whit
    0.99
    WHIT
    0.92
     Sympathi
    0.91
     Cæ
    0.91
     cappello
    0.88
    whit
    0.87
     Whitman
    0.85
    Activations Density 0.709%

    No Known Activations