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. 329
    Prev
    Next
    INDEX
    Explanations

    numerical values within specific formatting

    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
    1343
    +0.24
    0.7%
    394
    +0.11
    0.3%
    1531
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.24
    0.06
    1429
    +0.11
    0.05
    178
    +0.10
    0.04
    Negative Logits
    SourceChecksum
    -0.69
    LookAnd
    -0.62
     otomatig
    -0.59
    setViewportView
    -0.59
    tığı
    -0.58
     moment
    -0.58
    complexContent
    -0.58
    UnusedPrivate
    -0.57
    Diwedd
    -0.55
    TargetApi
    -0.55
    POSITIVE LOGITS
     §.
    1.53
     sii
    1.50
     sappi
    1.48
     vogli
    1.43
     ciao
    1.42
     Cfr
    1.41
     FFFF
    1.40
     »>
    1.39
     |]
    1.39
     napoli
    1.38
    Activations Density 0.136%

    No Known Activations