© 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. 1445
    Prev
    Next
    INDEX
    Explanations

    words related to video file conversion and software tools

    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
    938
    +0.08
    0.2%
    1086
    +0.07
    0.2%
    330
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.02
    1343
    +0.07
    0.07
    690
    +0.07
    0.06
    Negative Logits
     let
    -0.65
     fas
    -0.65
     mod
    -0.61
     sob
    -0.61
     cha
    -0.60
     comp
    -0.60
     desc
    -0.59
     ser
    -0.59
     scal
    -0.59
     pro
    -0.58
    POSITIVE LOGITS
     vété
    1.54
     Mère
    1.25
     carrefour
    1.17
     Docteur
    1.16
     noël
    1.16
     broderie
    1.16
     héro
    1.13
     pavillon
    1.12
     élev
    1.11
     veau
    1.11
    Activations Density 0.551%

    No Known Activations