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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15193
    Prev
    Next
    INDEX
    Explanations

    references related to TV show appearances

    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
    599
    +0.13
    0.4%
    1533
    +0.09
    0.3%
    198
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.13
    0.08
    940
    +0.09
    0.03
    981
    +0.09
    0.07
    Negative Logits
     $(\%)$
    -1.05
     maksi
    -0.94
     Byp
    -0.87
     osal
    -0.87
    (%)
    -0.85
     Expt
    -0.85
     pollut
    -0.84
     unlaw
    -0.84
     dovr
    -0.84
     disagre
    -0.83
    POSITIVE LOGITS
    <bos>
    1.00
     hilarious
    0.66
     sitcom
    0.64
     comedy
    0.64
    WebMethod
    0.62
     humor
    0.60
     comedic
    0.59
    Попис
    0.58
    kloped
    0.55
    Kanpo
    0.53
    Activations Density 0.920%

    No Known Activations