© 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. 1702
    Prev
    Next
    INDEX
    Explanations

    names of locations or companies related to telecommunications

    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
    228
    +0.10
    0.3%
    893
    +0.09
    0.3%
    78
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.03
    283
    +0.09
    0.01
    1363
    +0.08
    0.02
    Negative Logits
    omaterial
    -0.75
     expel
    -0.63
    onucleotide
    -0.63
    ometrial
    -0.62
    ophosph
    -0.60
    tilizer
    -0.57
    furan
    -0.56
    orrhea
    -0.55
    inosi
    -0.55
    omaterials
    -0.54
    POSITIVE LOGITS
    oc
    2.65
    OC
    2.23
     oc
    1.95
    Oc
    1.94
     Oc
    1.94
     OC
    1.91
    ocs
    1.41
     Koc
    1.25
     BOC
    1.20
     OCS
    1.16
    Activations Density 0.211%

    No Known Activations