© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2245
    Prev
    Next
    INDEX
    Explanations

    phrases related to speed or urgency

    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
    +0.14
    0.4%
    1983
    +0.09
    0.2%
    1776
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1776
    +0.14
    0.02
    1037
    +0.09
    0.02
    554
    +0.09
    0.03
    Negative Logits
     gaily
    -1.17
     unspeak
    -1.16
     reluct
    -1.12
     apprehen
    -1.07
     ineffec
    -1.05
     shenan
    -1.00
     disagre
    -0.99
     Juf
    -0.98
     indescri
    -0.96
     unlaw
    -0.95
    POSITIVE LOGITS
     possible
    0.86
     posible
    0.71
    possible
    0.70
     possibile
    0.67
    <bos>
    0.65
     POSSIBLE
    0.63
    Possible
    0.61
     anty
    0.60
     possível
    0.59
     possibles
    0.59
    Activations Density 0.099%

    No Known Activations