© 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. 14681
    Prev
    Next
    INDEX
    Explanations

    statements related to decision-making or critical thinking

    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
    1108
    +0.29
    1.1%
    599
    +0.23
    0.9%
    998
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1108
    +0.29
    0.09
    599
    +0.23
    0.07
    1819
    +0.15
    0.08
    Negative Logits
     fta
    -1.11
     ftu
    -1.00
     NOO
    -0.99
    Ikr
    -0.97
    «<
    -0.97
     fuf
    -0.96
     fto
    -0.95
     fte
    -0.95
     purcha
    -0.95
     effe
    -0.94
    POSITIVE LOGITS
     OMITBAD
    0.57
    CELLANEOUS
    0.56
     виправивши
    0.52
    cellaneous
    0.50
    becue
    0.49
    atiable
    0.48
    </strong>
    0.48
    AnchorStyles
    0.47
    .
    0.45
     prostu
    0.44
    Activations Density 1.019%

    No Known Activations