© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3380
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and advice

    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
    +0.10
    0.3%
    1763
    +0.08
    0.2%
    624
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    992
    +0.10
    0.02
    1475
    +0.08
    0.01
    870
    +0.07
    0.02
    Negative Logits
     Juf
    -1.11
     excru
    -1.09
     impra
    -1.09
     fuf
    -1.08
     disagre
    -1.06
     vété
    -1.05
     pitié
    -1.02
     reluct
    -1.02
     véhic
    -1.01
     confé
    -1.00
    POSITIVE LOGITS
    PostExecute
    0.65
     better
    0.62
     more
    0.62
     easier
    0.61
     stronger
    0.56
     nonatomic
    0.54
     closer
    0.54
     sooner
    0.54
     less
    0.53
    <bos>
    0.53
    Activations Density 0.060%

    No Known Activations