© 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. 12057
    Prev
    Next
    INDEX
    Explanations

    words related to medical treatments and their effects

    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
    876
    +0.13
    0.4%
    283
    +0.09
    0.3%
    736
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1801
    +0.13
    0.02
    1380
    +0.09
    0.01
    844
    +0.08
    0.03
    Negative Logits
    SourceChecksum
    -0.56
     kohdetta
    -0.55
     estekak
    -0.54
    npj
    -0.51
    Enllaços
    -0.50
    Cyfeiriadau
    -0.50
    正当
    -0.50
    Sqft
    -0.49
    脚注の使い方
    -0.49
    省市镇
    -0.49
    POSITIVE LOGITS
     disagre
    1.13
     unlaw
    1.06
     eyel
    1.05
     milf
    1.04
     apprehen
    1.02
     ecru
    0.95
     unwarran
    0.95
     hairc
    0.94
     shenan
    0.92
     guarante
    0.92
    Activations Density 0.224%

    No Known Activations