© 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. 4029
    Prev
    Next
    INDEX
    Explanations

    phrases with the structure "as a (positive trait or role)" or "as a (negative trait or role)"

    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
    1520
    +0.10
    0.3%
    1464
    +0.08
    0.3%
    893
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1129
    +0.10
    0.05
    1984
    +0.08
    0.04
    16
    +0.08
    0.04
    Negative Logits
     reluct
    -1.74
     maneu
    -1.58
     shenan
    -1.56
     apprehen
    -1.55
     disagre
    -1.51
     unspeak
    -1.47
     intersper
    -1.44
     depic
    -1.42
     encomp
    -1.39
     uninten
    -1.39
    POSITIVE LOGITS
    Sebagai
    0.65
     viewType
    0.65
     paradigma
    0.64
    osoba
    0.61
     سكانية
    0.61
    apropri
    0.58
     as
    0.58
     BoxDecoration
    0.57
     τὴν
    0.56
    styleType
    0.56
    Activations Density 0.207%

    No Known Activations