© 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. 5394
    Prev
    Next
    INDEX
    Explanations

    positive news statements

    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
    674
    +0.10
    0.3%
    2034
    +0.09
    0.3%
    1129
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2030
    +0.10
    0.03
    1839
    +0.09
    0.04
    1675
    +0.09
    0.04
    Negative Logits
     fatis
    -0.96
     fuf
    -0.95
     thut
    -0.82
     nece
    -0.82
     emphat
    -0.82
     „,
    -0.81
     effe
    -0.81
     myn
    -0.80
     affor
    -0.79
     ?...
    -0.79
    POSITIVE LOGITS
    Bad
    0.62
    bad
    0.61
     Good
    0.61
    Good
    0.61
    good
    0.59
     Bad
    0.59
     bad
    0.58
     good
    0.55
     AssemblyTitle
    0.55
     GOOD
    0.55
    Activations Density 0.290%

    No Known Activations