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. 15386
    Prev
    Next
    INDEX
    Explanations

    words related to purity or cleanliness

    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
    1325
    +0.11
    0.4%
    680
    +0.11
    0.4%
    938
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    938
    +0.11
    0.02
    680
    +0.11
    0.01
    1325
    +0.10
    0.01
    Negative Logits
     metálico
    -0.51
     bakteri
    -0.48
     débil
    -0.48
    ôtel
    -0.48
     Newspapers
    -0.48
     redondo
    -0.47
     extraña
    -0.45
     contemporánea
    -0.45
     metálica
    -0.44
     vacía
    -0.43
    POSITIVE LOGITS
     PURE
    1.22
    pure
    1.18
    Pure
    1.14
     pure
    1.14
     Pure
    1.11
    PURE
    1.05
     uncin
    0.94
     purity
    0.93
     pura
    0.85
     cytoplas
    0.84
    Activations Density 0.064%

    No Known Activations