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. 5525
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and possessive pronouns followed by "And" and "My"

    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
    1482
    +0.13
    0.7%
    61
    +0.11
    0.6%
    325
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1187
    +0.13
    0.04
    144
    +0.11
    0.04
    11
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.10
    miyor
    -0.89
    mişti
    -0.80
    iyor
    -0.72
    /*++
    -0.71
    diğini
    -0.69
    diğinde
    -0.67
    miyorum
    -0.67
    diğ
    -0.63
     distribute
    -0.60
    POSITIVE LOGITS
     Me
    1.28
    Me
    1.24
     Mej
    1.15
     Intere
    1.08
     Megal
    1.07
     compréhen
    1.07
     ME
    1.07
     Middles
    1.06
     Mezz
    1.06
     ecru
    1.03
    Activations Density 0.347%

    No Known Activations