© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 787
    Prev
    Next
    INDEX
    Explanations

    phrases related to speech acts and expressions of impossibility

    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
    1150
    +0.20
    0.6%
    674
    +0.18
    0.5%
    1343
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1150
    +0.20
    0.04
    845
    +0.18
    0.06
    284
    +0.13
    0.07
    Negative Logits
    Glej
    -0.82
    Pozri
    -0.63
    Transcrip
    -0.59
    Zgod
    -0.55
     Pued
    -0.53
    Vegeu
    -0.53
     Quien
    -0.52
     tambi
    -0.52
    $+\
    -0.50
     resalt
    -0.50
    POSITIVE LOGITS
    <bos>
    0.75
     împre
    0.56
     anteriorly
    0.54
    商品説明
    0.54
    存于互联网档案馆
    0.54
    setof
    0.53
    Билгалдахарш
    0.53
     soste
    0.52
    rehensive
    0.52
     CHECKBOX
    0.50
    Activations Density 0.672%

    No Known Activations