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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 187
    Prev
    Next
    INDEX
    Explanations

    mentions of political and policy-related terms and concepts

    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
    1870
    +0.24
    0.7%
    1385
    +0.11
    0.3%
    1978
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.24
    0.06
    74
    +0.11
    0.05
    426
    +0.11
    0.05
    Negative Logits
     disagre
    -1.61
     reluct
    -1.58
     impra
    -1.56
     unspeak
    -1.54
     fortn
    -1.52
     gaily
    -1.48
     indescri
    -1.46
     affor
    -1.45
     apprehen
    -1.44
     depic
    -1.43
    POSITIVE LOGITS
     capabilities
    0.76
     abilities
    0.72
     efforts
    0.72
     activities
    0.67
     ability
    0.67
     habits
    0.67
     strategy
    0.66
     profile
    0.65
     goals
    0.65
     journey
    0.64
    Activations Density 0.412%

    No Known Activations