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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8855
    Prev
    Next
    INDEX
    Explanations

    dates or specific days of the week related to events or activities

    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
    +0.14
    0.4%
    1137
    +0.10
    0.3%
    1077
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1663
    +0.14
    0.04
    223
    +0.10
    0.04
    776
    +0.09
    0.04
    Negative Logits
    <bos>
    -1.00
    Xuất
    -0.69
    Ảnh
    -0.67
    Tác
    -0.65
    Phân
    -0.65
    YECTO
    -0.64
    Năm
    -0.64
    VIAF
    -0.63
    Về
    -0.62
    Hình
    -0.61
    POSITIVE LOGITS
     maneu
    1.56
     reluct
    1.54
     indestru
    1.53
     disgra
    1.48
     disagre
    1.46
     shenan
    1.45
     excru
    1.44
     erad
    1.43
     affor
    1.43
     accla
    1.37
    Activations Density 0.192%

    No Known Activations