© 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. 6875
    Prev
    Next
    INDEX
    Explanations

    words related to blaming or assigning responsibility

    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
    +0.11
    0.3%
    1420
    +0.07
    0.2%
    1042
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1420
    +0.11
    0.04
    1477
    +0.07
    0.04
    683
    +0.06
    0.04
    Negative Logits
     maneu
    -1.23
     depic
    -1.17
     shenan
    -1.14
     gaily
    -1.12
     reluct
    -1.11
     encomp
    -1.07
     jurassic
    -1.07
     disagre
    -1.06
     stockholm
    -1.05
     Confu
    -1.04
    POSITIVE LOGITS
     appropriate
    0.75
    HtmlAttribute
    0.75
     proper
    0.73
    BeginInit
    0.69
     indeb
    0.68
    apropri
    0.68
     INSEE
    0.65
     nakalista
    0.64
     meras
    0.64
     notor
    0.63
    Activations Density 0.323%

    No Known Activations