Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14051
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or political controversies

    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
    1013
    +0.17
    0.5%
    2034
    +0.10
    0.3%
    1870
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.17
    0.10
    284
    +0.10
    0.08
    690
    +0.09
    0.03
    Negative Logits
     affor
    -2.21
     increa
    -2.19
     purcha
    -2.18
     encomp
    -2.16
     scrat
    -2.03
     fuf
    -2.03
     emphat
    -2.02
     volunte
    -2.01
     peppa
    -2.00
     guarante
    -1.98
    POSITIVE LOGITS
    .
    0.95
    ;
    0.86
     again
    0.82
    .;
    0.79
    。
    0.77
    ,
    0.76
     with
    0.75
     due
    0.75
     and
    0.74
     but
    0.73
    Activations Density 0.820%

    No Known Activations