© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12828
    Prev
    Next
    INDEX
    Explanations

    terms related to political discussions and legislative activities, focusing on phrases and roles within these contexts

    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
    1177
    +0.11
    0.3%
    513
    +0.10
    0.3%
    490
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    513
    +0.11
    0.06
    490
    +0.10
    0.04
    1095
    +0.08
    0.04
    Negative Logits
     paralel
    -0.62
     itali
    -0.59
     frans
    -0.59
     koz
    -0.57
     katal
    -0.57
     bicic
    -0.55
    phrag
    -0.55
    GraphicsUnit
    -0.55
     hObject
    -0.55
     polig
    -0.55
    POSITIVE LOGITS
     unwarran
    1.44
     disagre
    1.38
     reluct
    1.33
     unlaw
    1.31
     unspeak
    1.30
     inconce
    1.26
     impractica
    1.25
     apprehen
    1.23
     uninten
    1.18
     gaily
    1.16
    Activations Density 0.372%

    No Known Activations