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. 14634
    Prev
    Next
    INDEX
    Explanations

    strings related to legal agreements and regulations

    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
    50
    +0.31
    1.5%
    1967
    +0.10
    0.5%
    478
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.31
    0.12
    1407
    +0.10
    0.09
    1023
    +0.09
    0.09
    Negative Logits
    <bos>
    -3.66
     that
    -0.76
     and
    -0.75
    ,
    -0.75
    ModelAdmin
    -0.75
     don
    -0.72
    、
    -0.72
    util
    -0.72
    complexType
    -0.71
     for
    -0.71
    POSITIVE LOGITS
     stockholm
    2.34
     accla
    2.29
     maneu
    2.25
     milf
    2.24
     affor
    2.22
     shenan
    2.22
     reluct
    2.16
     volunte
    2.16
     increa
    2.15
     practition
    2.14
    Activations Density 1.124%

    No Known Activations