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. 15492
    Prev
    Next
    INDEX
    Explanations

    information related to news articles

    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
    2019
    +0.21
    0.7%
    1445
    +0.15
    0.5%
    1741
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1445
    +0.21
    0.07
    382
    +0.15
    0.06
    1265
    +0.13
    0.05
    Negative Logits
     deleter
    -1.21
     maroc
    -1.16
     nutr
    -1.16
     sopr
    -1.16
     embodi
    -1.14
     toscana
    -1.13
     applau
    -1.12
     milano
    -1.12
    !!</
    -1.10
     peculi
    -1.10
    POSITIVE LOGITS
     we
    0.78
     however
    0.76
     there
    0.74
     they
    0.71
     it
    0.71
     you
    0.69
     though
    0.68
     while
    0.66
     when
    0.66
     he
    0.65
    Activations Density 0.268%

    No Known Activations