© 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. 3744
    Prev
    Next
    INDEX
    Explanations

    phrases related to satire and entertainment industry critiques

    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
    872
    +0.10
    0.3%
    764
    +0.10
    0.3%
    1533
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    816
    +0.10
    0.04
    872
    +0.10
    0.06
    963
    +0.08
    0.04
    Negative Logits
     chrysler
    -1.09
     Standardi
    -1.08
     mitsubishi
    -1.06
     isuzu
    -1.03
     silikon
    -1.02
     michelin
    -1.01
     Intere
    -1.00
     naer
    -0.99
     alkoh
    -0.99
     maksi
    -0.99
    POSITIVE LOGITS
     smtplib
    0.61
    WriteBarrier
    0.56
     relatable
    0.56
    Fordítás
    0.55
     satire
    0.55
     portray
    0.55
    Становништво
    0.53
    yticks
    0.52
     portrayal
    0.52
     pymysql
    0.52
    Activations Density 0.448%

    No Known Activations