© 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. 0-RES-JB
    11. 1603
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations, individuals, or topics related to political events or discussions

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1753
    +0.09
    0.2%
    292
    +0.08
    0.2%
    1420
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.09
    0.05
    1343
    +0.08
    0.09
    1927
    +0.07
    0.08
    Negative Logits
     so
    -0.88
    AxisAlignment
    -0.85
     ten
    -0.85
     e
    -0.84
     to
    -0.84
    ,
    -0.81
     ver
    -0.81
    </em>
    -0.80
     too
    -0.80
     but
    -0.80
    POSITIVE LOGITS
     ftu
    3.00
     desir
    2.77
     fta
    2.77
     emphat
    2.77
     thut
    2.75
     increa
    2.75
     fuf
    2.73
     inev
    2.72
     maneu
    2.70
     !...
    2.66
    Activations Density 0.520%

    No Known Activations