© 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. 3837
    Prev
    Next
    INDEX
    Explanations

    phrases related to reputation and personal growth

    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
    297
    +0.12
    0.4%
    1265
    +0.11
    0.3%
    1363
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.12
    0.07
    1948
    +0.11
    0.06
    136
    +0.10
    0.03
    Negative Logits
     encomp
    -0.96
     boî
    -0.89
     négociations
    -0.88
    Rgds
    -0.86
     nece
    -0.86
     opport
    -0.85
     volunte
    -0.85
     coö
    -0.84
     gouvernements
    -0.84
     perfon
    -0.82
    POSITIVE LOGITS
    GraphicsUnit
    0.71
     themselves
    0.69
    HostException
    0.66
    STRUCTIONS
    0.66
     podjela
    0.64
     serializers
    0.62
    rophes
    0.62
    assies
    0.61
    êques
    0.61
    ticides
    0.61
    Activations Density 0.613%

    No Known Activations