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. 15840
    Prev
    Next
    INDEX
    Explanations

    numerical values related to the frequency of events over time

    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
    1042
    +0.09
    0.3%
    674
    +0.08
    0.2%
    321
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    54
    +0.09
    0.04
    246
    +0.08
    0.03
    776
    +0.08
    0.04
    Negative Logits
     adal
    -0.77
    tificates
    -0.66
     kac
    -0.65
     karte
    -0.63
     augus
    -0.61
    gruntled
    -0.58
    ?«
    -0.58
     BIBSYS
    -0.58
     hina
    -0.57
    TextInputLayout
    -0.57
    POSITIVE LOGITS
     vainly
    0.83
     nutella
    0.82
     shenan
    0.80
     impelled
    0.78
     subgoal
    0.77
     Wtf
    0.74
     ingrat
    0.73
     indestru
    0.73
    Fuckin
    0.73
    Jeez
    0.72
    Activations Density 0.156%

    No Known Activations