© 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. 1166
    Prev
    Next
    INDEX
    Explanations

    the name "issing"

    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
    313
    +0.09
    0.3%
    1806
    +0.09
    0.3%
    240
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.03
    283
    +0.09
    0.01
    590
    +0.09
    0.02
    Negative Logits
     recover
    -0.58
     recovered
    -0.57
     regain
    -0.57
     mõ
    -0.54
    ゴリー
    -0.53
     taip
    -0.53
     recovers
    -0.52
     kõik
    -0.52
     could
    -0.52
     put
    -0.51
    POSITIVE LOGITS
    iss
    2.98
    ISS
    2.13
     iss
    1.64
    Iss
    1.46
    issu
    1.41
    isses
    1.30
     ISS
    1.27
     squa
    1.27
     fup
    1.26
     noss
    1.25
    Activations Density 0.191%

    No Known Activations