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. 15351
    Prev
    Next
    INDEX
    Explanations

    quotes from different individuals in various contexts

    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
    1150
    +0.21
    0.6%
    889
    +0.10
    0.3%
    1068
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1150
    +0.21
    0.04
    889
    +0.10
    0.05
    395
    +0.08
    0.05
    Negative Logits
     swarovski
    -1.31
     murano
    -1.20
     dispen
    -1.16
     effe
    -1.14
     vespa
    -1.12
     NOO
    -1.11
     increa
    -1.10
     desir
    -1.10
     cabrio
    -1.10
     erec
    -1.10
    POSITIVE LOGITS
    said
    0.77
     said
    0.75
    .
    0.66
    Said
    0.61
    .”
    0.60
     says
    0.59
     Tuesday
    0.57
     during
    0.57
     Said
    0.57
     saying
    0.57
    Activations Density 0.127%

    No Known Activations