© 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. 16317
    Prev
    Next
    INDEX
    Explanations

    dates and time references

    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
    2034
    +0.15
    0.4%
    856
    +0.11
    0.3%
    1150
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    856
    +0.15
    0.06
    1830
    +0.11
    0.04
    1444
    +0.09
    0.04
    Negative Logits
     effe
    -1.33
     nece
    -1.25
     !...
    -1.23
     ?...
    -1.23
     desir
    -1.22
     NOO
    -1.19
     Ottobre
    -1.18
     aen
    -1.18
     doman
    -1.12
     carc
    -1.11
    POSITIVE LOGITS
    .
    0.67
    。
    0.59
     or
    0.59
     tomorrow
    0.58
     if
    0.56
     according
    0.55
     arşivlendi
    0.55
    .”
    0.54
     unless
    0.54
    ."
    0.54
    Activations Density 0.250%

    No Known Activations