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. 15434
    Prev
    Next
    INDEX
    Explanations

    mentions of empty or evacuated buildings and coffins

    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
    1222
    +0.13
    0.4%
    897
    +0.12
    0.4%
    1964
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1233
    +0.13
    0.02
    1222
    +0.12
    0.02
    1964
    +0.11
    0.02
    Negative Logits
     affor
    -1.09
     unspeak
    -1.01
     increa
    -0.96
     impra
    -0.95
     disagre
    -0.94
     indescri
    -0.93
     unlaw
    -0.92
     guarante
    -0.88
     inconce
    -0.88
     fortn
    -0.86
    POSITIVE LOGITS
     empty
    1.20
    empty
    1.14
     Empty
    1.09
    Empty
    1.08
    EMPTY
    0.92
     EMPTY
    0.86
     emptied
    0.80
    mpty
    0.79
     vacant
    0.77
    isEmpty
    0.75
    Activations Density 0.086%

    No Known Activations