© 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. 2539
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal reflection and internal struggle

    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
    900
    +0.13
    0.4%
    67
    +0.10
    0.3%
    411
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    900
    +0.13
    0.07
    581
    +0.10
    0.06
    438
    +0.10
    0.06
    Negative Logits
     lele
    -1.21
     marte
    -1.14
     Châ
    -1.12
     kram
    -1.12
     Mémoires
    -1.09
     budapest
    -1.08
     endom
    -1.04
     poire
    -1.04
     fei
    -1.04
     franz
    -1.03
    POSITIVE LOGITS
     necessarily
    0.73
     przecież
    0.67
    Może
    0.66
    doesn
    0.65
     doesnt
    0.63
    t
    0.63
     really
    0.63
     niestety
    0.61
     siquiera
    0.61
    Dzięki
    0.61
    Activations Density 0.166%

    No Known Activations