© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 3331
    Prev
    Next
    INDEX
    Explanations

    financial terms and investment-related information

    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
    1967
    +0.36
    1.5%
    1438
    +0.18
    0.8%
    738
    +0.18
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.36
    0.12
    1385
    +0.18
    0.21
    1343
    +0.18
    0.21
    Negative Logits
    <bos>
    -3.71
    Autoritní
    -1.54
     autorytatywna
    -1.39
    @[+][
    -1.30
    SourceChecksum
    -1.26
    DockStyle
    -1.23
     ModelExpression
    -1.21
     ویکی‌پدی
    -1.21
     bezeichneter
    -1.19
     pamph
    -1.19
    POSITIVE LOGITS
    .
    0.64
    ↵↵
    0.59
     alike
    0.57
    ).
    0.54
     etc
    0.52
     thereof
    0.52
     an
    0.52
    ↵↵↵
    0.51
     .
    0.51
     others
    0.51
    Activations Density 4.955%

    No Known Activations