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. 1534
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Sessions"

    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
    1065
    +0.14
    0.6%
    1870
    +0.12
    0.5%
    1416
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1065
    +0.14
    0.02
    1059
    +0.12
    0.02
    1516
    +0.12
    0.02
    Negative Logits
     chio
    -0.49
    schwar
    -0.44
     médaille
    -0.43
     notor
    -0.43
     Stä
    -0.42
     compil
    -0.42
     agenti
    -0.42
     CHU
    -0.42
     EoL
    -0.41
     prenota
    -0.41
    POSITIVE LOGITS
     session
    1.45
     Session
    1.39
     sessions
    1.35
     Sessions
    1.35
    session
    1.28
    Session
    1.26
     SESSION
    1.23
    Sessions
    1.19
    sessions
    1.15
    SESSION
    1.15
    Activations Density 0.092%

    No Known Activations