Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2756
    Prev
    Next
    INDEX
    Explanations

    sports event details, such as scores, players' names, teams, and dates

    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
    674
    +0.15
    0.4%
    1804
    +0.10
    0.3%
    1967
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1804
    +0.15
    0.03
    1850
    +0.10
    0.03
    2012
    +0.10
    0.03
    Negative Logits
     unspeak
    -1.26
     vainly
    -0.93
     apprehen
    -0.93
     impelled
    -0.91
     thoughtless
    -0.90
     ruddy
    -0.89
     quivering
    -0.84
     sophistic
    -0.84
     mischie
    -0.82
     deluded
    -0.82
    POSITIVE LOGITS
     utop
    1.95
     alkoh
    1.92
     marte
    1.86
     incess
    1.78
     solidar
    1.77
     manuten
    1.75
     vola
    1.74
     ordina
    1.71
     meras
    1.69
     drap
    1.67
    Activations Density 0.058%

    No Known Activations