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. 13992
    Prev
    Next
    INDEX
    Explanations

    references to official documents or directives

    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
    +0.13
    0.4%
    690
    +0.13
    0.4%
    1978
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1435
    +0.13
    0.06
    382
    +0.13
    0.05
    994
    +0.13
    0.04
    Negative Logits
    født
    -0.70
    SneakyThrows
    -0.67
     saites
    -0.65
    istoitu
    -0.58
     antwortete
    -0.55
    astéro
    -0.55
    XmlAccessorType
    -0.55
    妬
    -0.52
     rocas
    -0.52
    ülerin
    -0.52
    POSITIVE LOGITS
     maneu
    1.93
     increa
    1.91
     depic
    1.90
     inev
    1.89
     encomp
    1.84
     impra
    1.81
     disagre
    1.80
     shenan
    1.73
     apprehen
    1.71
     reluct
    1.70
    Activations Density 0.266%

    No Known Activations