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. 10003
    Prev
    Next
    INDEX
    Explanations

    references to processes involving linked or sequential steps

    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
    1262
    +0.16
    0.6%
    1425
    +0.15
    0.6%
    67
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1425
    +0.16
    0.03
    1262
    +0.15
    0.02
    67
    +0.13
    0.02
    Negative Logits
    렷
    -0.58
    iquest
    -0.51
    PreAuthorize
    -0.50
     Bajos
    -0.48
    Rptr
    -0.47
     كومونز
    -0.47
    Sản
    -0.46
    laquo
    -0.46
    FetchType
    -0.46
     Obrador
    -0.45
    POSITIVE LOGITS
     chain
    1.43
     Chain
    1.37
    chain
    1.36
     CHAIN
    1.32
     chains
    1.32
    Chain
    1.27
     Chains
    1.25
    chains
    1.18
     chaining
    1.15
    Chains
    1.14
    Activations Density 0.066%

    No Known Activations