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. 8219
    Prev
    Next
    INDEX
    Explanations

    weapons-related terms, tools, and procedures

    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
    845
    +0.09
    0.3%
    1842
    +0.09
    0.3%
    1978
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1483
    +0.09
    0.04
    1856
    +0.09
    0.05
    246
    +0.08
    0.03
    Negative Logits
     dè
    -0.85
     makro
    -0.84
     ló
    -0.83
     antik
    -0.81
     utop
    -0.81
     liev
    -0.80
     Kategor
    -0.79
     RSSSF
    -0.76
     NKC
    -0.76
     legenda
    -0.74
    POSITIVE LOGITS
     unspeak
    1.27
     indescri
    1.12
     apprehen
    1.07
     tolerably
    1.06
     reluct
    1.03
     vainly
    1.02
     inconce
    1.01
     quitted
    1.00
     impra
    0.99
     disagre
    0.99
    Activations Density 0.534%

    No Known Activations