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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6633
    Prev
    Next
    INDEX
    Explanations

    information about self-acceptance and self-improvement

    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
    1533
    +0.08
    0.2%
    2006
    +0.07
    0.2%
    1446
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.08
    0.02
    1580
    +0.07
    0.03
    825
    +0.07
    0.02
    Negative Logits
     maneu
    -1.61
     reluct
    -1.54
     depic
    -1.52
     shenan
    -1.52
     encomp
    -1.51
     increa
    -1.46
     intersper
    -1.43
     attemp
    -1.43
     guarante
    -1.42
     accla
    -1.41
    POSITIVE LOGITS
    <bos>
    1.07
    SneakyThrows
    0.81
     yourself
    0.74
    PyExc
    0.71
     myself
    0.65
     وتسجيلات
    0.64
     Paglinawan
    0.63
     ourselves
    0.62
    SharedDtor
    0.61
    AutoScaleMode
    0.60
    Activations Density 0.416%

    No Known Activations