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. 135
    Prev
    Next
    INDEX
    Explanations

    movie titles

    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
    1047
    +0.12
    0.7%
    1178
    +0.12
    0.7%
    555
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.12
    0.07
    227
    +0.12
    0.07
    1343
    +0.12
    0.07
    Negative Logits
    <bos>
    -2.15
    guang
    -0.70
    sheng
    -0.66
    fillType
    -0.64
    qiao
    -0.61
    yao
    -0.61
    zhong
    -0.58
    springframework
    -0.57
    묶
    -0.56
    usercontent
    -0.56
    POSITIVE LOGITS
     affor
    1.51
     indestru
    1.48
     unwarran
    1.39
     maneu
    1.38
     LXXX
    1.36
     increa
    1.35
     scrat
    1.35
     perfet
    1.35
     excru
    1.35
     emphat
    1.34
    Activations Density 0.484%

    No Known Activations