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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15203
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific organization in the veterinary field, particularly focused on diagnostic imaging

    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
    1437
    +0.15
    0.8%
    1034
    +0.14
    0.7%
    1103
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1437
    +0.15
    0.04
    227
    +0.14
    0.05
    783
    +0.13
    0.03
    Negative Logits
    <bos>
    -0.69
    DockStyle
    -0.58
    Obra
    -0.57
    Пото
    -0.57
    parsedMessage
    -0.56
    typeorm
    -0.56
    artifactId
    -0.56
    WebpackPlugin
    -0.55
    Comun
    -0.55
    setIcon
    -0.55
    POSITIVE LOGITS
     Vet
    1.13
    Vet
    0.98
     pamph
    0.96
     vet
    0.94
     maneu
    0.94
     impra
    0.91
     subgoals
    0.91
     Ename
    0.90
     hairc
    0.89
     embodi
    0.89
    Activations Density 0.514%

    No Known Activations