© 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. 15231
    Prev
    Next
    INDEX
    Explanations

    words related to mistakes or errors

    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
    1350
    +0.13
    0.4%
    468
    +0.10
    0.4%
    1548
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.13
    0.03
    2000
    +0.10
    0.03
    468
    +0.10
    0.03
    Negative Logits
     guarante
    -0.75
     depic
    -0.75
     alre
    -0.71
     attemp
    -0.68
     endeavouring
    -0.68
     intersper
    -0.68
     unspeak
    -0.67
     ?...
    -0.67
     ineffec
    -0.65
     impractica
    -0.64
    POSITIVE LOGITS
    wrong
    1.01
     wrong
    0.98
    Wrong
    0.97
     Wrong
    0.91
     WRONG
    0.79
    WRONG
    0.77
     OMITBAD
    0.65
    Geplaatst
    0.64
     AssemblyCulture
    0.63
     wrongs
    0.63
    Activations Density 0.067%

    No Known Activations