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. 6081
    Prev
    Next
    INDEX
    Explanations

    references to parallel processes or systems

    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
    545
    +0.14
    0.7%
    1407
    +0.14
    0.7%
    120
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1272
    +0.14
    0.02
    1137
    +0.14
    0.03
    1052
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.68
    Гу
    -0.68
    rungsseite
    -0.64
    受
    -0.64
    cookie
    -0.63
     խ
    -0.59
    අ
    -0.59
    pub
    -0.58
    ઊ
    -0.58
     تع
    -0.58
    POSITIVE LOGITS
     suspic
    1.63
     affor
    1.56
     desir
    1.51
     emphat
    1.50
     madonna
    1.49
     fta
    1.48
     perfet
    1.48
     ftu
    1.47
     foon
    1.46
     Juf
    1.45
    Activations Density 0.322%

    No Known Activations