© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 5532
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and the verb 'was'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1919
    +0.14
    0.4%
    1533
    +0.14
    0.4%
    184
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.14
    0.12
    1438
    +0.14
    0.06
    862
    +0.11
    0.04
    Negative Logits
     canel
    -1.44
     swarovski
    -1.41
     peppa
    -1.39
     fluo
    -1.32
     matel
    -1.30
     bordeaux
    -1.28
     endom
    -1.21
     oleo
    -1.20
     napoli
    -1.20
     tupperware
    -1.15
    POSITIVE LOGITS
     didn
    1.16
     had
    1.16
     was
    1.14
     lacked
    1.13
     wasn
    1.11
     did
    1.09
     gave
    1.07
     went
    1.07
     took
    1.06
     were
    1.05
    Activations Density 0.675%

    No Known Activations