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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 864
    Prev
    Next
    INDEX
    Explanations

    references to entities or compounds in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    528
    +0.15
    0.9%
    1145
    +0.15
    0.9%
    1335
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.15
    0.09
    227
    +0.15
    0.08
    1145
    +0.13
    0.05
    Negative Logits
    <bos>
    -2.20
     opzioni
    -0.99
     applicazioni
    -0.93
     jette
    -0.90
     mantenga
    -0.89
     versioni
    -0.84
     encuentre
    -0.83
     considère
    -0.81
     reconnaît
    -0.81
     conseguenze
    -0.78
    POSITIVE LOGITS
     accla
    1.55
     uncin
    1.45
     maneu
    1.44
     unce
    1.42
     socie
    1.42
     affor
    1.42
     conspic
    1.41
     juven
    1.40
     reluct
    1.36
     unve
    1.35
    Activations Density 0.655%

    No Known Activations