© 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. 4907
    Prev
    Next
    INDEX
    Explanations

    locations within a narrative

    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
    1013
    +0.12
    0.3%
    1105
    +0.08
    0.2%
    1523
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1105
    +0.12
    0.05
    1013
    +0.08
    0.06
    1438
    +0.08
    0.04
    Negative Logits
     sergio
    -0.81
     jorge
    -0.80
     javier
    -0.77
     alberto
    -0.75
     impra
    -0.73
     roberto
    -0.72
     fuf
    -0.72
     edp
    -0.72
     leonardo
    -0.71
     milano
    -0.71
    POSITIVE LOGITS
     altogether
    0.62
     prematurely
    0.56
     abruptly
    0.52
     entirely
    0.52
    ㎖
    0.51
     khỏi
    0.51
     after
    0.51
    embley
    0.49
     due
    0.49
    WebVitals
    0.48
    Activations Density 0.342%

    No Known Activations