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. 10-RES-JB
    6. 1824
    Prev
    Next
    INDEX
    Explanations

    terms related to biological and chemical substances, particularly hormones and fitness-related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.26
    1.0%
    872
    +0.09
    0.3%
    394
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1095
    +0.26
    0.07
    1705
    +0.09
    0.06
    1870
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.86
    ɵɵ
    -0.76
    displayquote
    -0.75
    Autoritní
    -0.72
    EndProject
    -0.70
    <tfoot>
    -0.66
    govine
    -0.65
     &___
    -0.65
    AntiForgeryToken
    -0.63
     và
    -0.60
    POSITIVE LOGITS
     affor
    1.83
     unlaw
    1.77
     ecru
    1.74
     impra
    1.65
     hairc
    1.63
     increa
    1.58
     cushi
    1.57
     disagre
    1.53
     reluct
    1.51
     stockholm
    1.51
    Activations Density 0.979%

    No Known Activations