© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 16132
    Prev
    Next
    INDEX
    Explanations

    references to the character named "Grendel" and related variations

    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
    1575
    +0.15
    0.6%
    251
    +0.14
    0.6%
    553
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1575
    +0.15
    0.03
    1145
    +0.14
    0.03
    981
    +0.12
    0.03
    Negative Logits
    sizlik
    -0.50
    ApiModel
    -0.48
    HttpPut
    -0.48
    าหลี
    -0.47
    Супер
    -0.47
    Stiftung
    -0.46
     Tyler
    -0.45
     Aida
    -0.44
     Carolina
    -0.43
    toContain
    -0.43
    POSITIVE LOGITS
     Gre
    1.34
    Gre
    1.34
     gre
    1.23
     GRE
    1.13
    gre
    1.10
    GRE
    0.98
     jati
    0.96
     dises
    0.96
     eyel
    0.95
     hina
    0.89
    Activations Density 0.131%

    No Known Activations