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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 188
    Prev
    Next
    INDEX
    Explanations

    references to historical events and figures, as well as locations and dates

    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
    +0.19
    0.7%
    1980
    +0.07
    0.3%
    1055
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    882
    +0.19
    0.04
    509
    +0.07
    0.03
    527
    +0.06
    0.03
    Negative Logits
    <bos>
    -2.72
    public
    -0.67
    ConstraintMaker
    -0.66
    struct
    -0.64
     mergeFrom
    -0.61
    об
    -0.60
    addComponent
    -0.59
     earn
    -0.59
     prepare
    -0.59
    Autoritní
    -0.59
    POSITIVE LOGITS
     affor
    1.77
     increa
    1.68
     wherea
    1.66
     inev
    1.66
     reluct
    1.63
     emphat
    1.63
     accla
    1.62
     disagre
    1.61
     unden
    1.61
     squa
    1.60
    Activations Density 0.290%

    No Known Activations