© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11116
    Prev
    Next
    INDEX
    Explanations

    phrases related to mentorship and education

    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
    394
    +0.15
    0.5%
    1108
    +0.11
    0.4%
    184
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1533
    +0.15
    0.01
    184
    +0.11
    0.01
    942
    +0.10
    0.04
    Negative Logits
     ?...
    -1.37
     disagre
    -1.37
     NOO
    -1.34
     strick
    -1.30
     squa
    -1.30
     perfet
    -1.29
     !...
    -1.29
     secon
    -1.27
     encomp
    -1.27
     reluct
    -1.27
    POSITIVE LOGITS
    <bos>
    1.05
    Cześć
    0.71
    Apesar
    0.67
    Witaj
    0.64
    Vegeu
    0.63
    Muito
    0.59
    Ahoj
    0.58
    Conteúdo
    0.58
    GIVEREF
    0.57
    Conheça
    0.57
    Activations Density 0.402%

    No Known Activations