© 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. 7292
    Prev
    Next
    INDEX
    Explanations

    words related to telecommunications companies and acquisition deals

    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
    599
    +0.51
    2.1%
    612
    +0.12
    0.5%
    1166
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.51
    0.13
    845
    +0.12
    0.03
    227
    +0.10
    0.07
    Negative Logits
    IsContent
    -0.65
    shadowRadius
    -0.60
    rrggbb
    -0.60
     gawas
    -0.57
     fieldNum
    -0.57
    <bos>
    -0.57
    Bioaccumulative
    -0.53
     snippetHide
    -0.53
     Bioaccumulative
    -0.53
     wireType
    -0.52
    POSITIVE LOGITS
     milf
    1.03
     unlaw
    1.01
     depic
    1.00
     philanth
    0.98
     affor
    0.98
     Mlle
    0.96
     encomp
    0.96
     volunte
    0.95
     disagre
    0.94
     accla
    0.94
    Activations Density 1.032%

    No Known Activations