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. 13609
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing events

    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
    1967
    +0.10
    0.3%
    1085
    +0.09
    0.3%
    468
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.10
    0.03
    1085
    +0.09
    0.03
    261
    +0.09
    0.02
    Negative Logits
     vorrei
    -0.80
     trovo
    -0.74
     voglio
    -0.70
     vuol
    -0.67
     penso
    -0.63
     aspetta
    -0.61
     lentement
    -0.61
     faccio
    -0.60
     vogliamo
    -0.60
     facciamo
    -0.59
    POSITIVE LOGITS
     psycopg
    0.64
     ndarray
    0.61
     happening
    0.58
     DBG
    0.55
     inside
    0.51
     herre
    0.51
    Clik
    0.51
     behind
    0.51
     nmax
    0.51
     zipfile
    0.49
    Activations Density 0.147%

    No Known Activations