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. 8229
    Prev
    Next
    INDEX
    Explanations

    legal and political terms

    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
    1177
    +0.12
    0.4%
    1919
    +0.11
    0.3%
    1870
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.12
    0.08
    862
    +0.11
    0.05
    802
    +0.09
    0.06
    Negative Logits
     paradigma
    -0.69
     colch
    -0.68
     psicologia
    -0.66
     rimb
    -0.66
     cristian
    -0.65
     masaj
    -0.63
     feltro
    -0.62
     balon
    -0.61
     rosas
    -0.61
     antropo
    -0.61
    POSITIVE LOGITS
     reluct
    1.72
     disagre
    1.64
     unwarran
    1.58
     pamph
    1.53
     apprehen
    1.52
     inev
    1.52
     emphat
    1.51
     desir
    1.50
     depic
    1.49
     impra
    1.46
    Activations Density 0.394%

    No Known Activations