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. 1272
    Prev
    Next
    INDEX
    Explanations

    titles of comic books

    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
    1343
    +0.16
    0.5%
    50
    +0.09
    0.2%
    332
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.16
    0.03
    1108
    +0.09
    0.03
    358
    +0.07
    0.02
    Negative Logits
     apprehen
    -0.78
     reluct
    -0.73
     murmuring
    -0.65
     disagre
    -0.63
     shenan
    -0.62
     perchance
    -0.59
     pooh
    -0.59
     intersper
    -0.58
     vainly
    -0.58
     maneu
    -0.57
    POSITIVE LOGITS
     €€
    0.84
     €)
    0.82
     utop
    0.80
     revisor
    0.79
    Preparazione
    0.77
     sord
    0.74
     €/
    0.74
    €)
    0.74
     €,
    0.73
     abbra
    0.71
    Activations Density 0.075%

    No Known Activations