© 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. 1357
    Prev
    Next
    INDEX
    Explanations

    terms related to alignment and calibration, especially in the context of technical instruments

    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
    1306
    +0.08
    0.3%
    156
    +0.08
    0.2%
    1378
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1378
    +0.08
    0.03
    1306
    +0.08
    0.02
    54
    +0.08
    0.02
    Negative Logits
    velocityY
    -0.54
    marginHorizontal
    -0.53
    Voltar
    -0.51
    marginVertical
    -0.49
     connaissent
    -0.49
     multer
    -0.47
    <bos>
    -0.47
    glMatrixMode
    -0.47
     bonté
    -0.47
    Források
    -0.47
    POSITIVE LOGITS
     alignment
    2.70
     Alignment
    2.51
     aligned
    2.40
     alignments
    2.40
    alignment
    2.38
     align
    2.35
     Align
    2.33
     aligning
    2.29
    Alignment
    2.24
    align
    2.16
    Activations Density 0.145%

    No Known Activations