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. 5563
    Prev
    Next
    INDEX
    Explanations

    details related to cooking instructions and product specifications

    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
    1983
    +0.18
    0.9%
    1984
    +0.14
    0.8%
    1691
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1983
    +0.18
    0.04
    1984
    +0.14
    0.05
    783
    +0.14
    0.03
    Negative Logits
    <bos>
    -1.28
     bus
    -0.54
    emer
    -0.54
    ContentAlignment
    -0.52
    DrawerToggle
    -0.50
     Bowen
    -0.50
    Emer
    -0.50
     Hunter
    -0.49
     Emery
    -0.49
    Institu
    -0.49
    POSITIVE LOGITS
     AA
    1.14
     Février
    1.10
     milano
    1.03
     Ottobre
    1.03
     Giugno
    1.03
     Settembre
    1.02
     ricardo
    1.01
     Décembre
    0.98
     trion
    0.98
     giovanni
    0.97
    Activations Density 0.527%

    No Known Activations