Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14052
    Prev
    Next
    INDEX
    Explanations

    descriptions of emotional experiences and personal reflections

    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
    674
    +0.09
    0.3%
    290
    +0.06
    0.2%
    72
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1700
    +0.09
    0.03
    163
    +0.06
    0.02
    1817
    +0.06
    0.03
    Negative Logits
     Khart
    -0.98
     philanth
    -0.90
     Juf
    -0.89
     roberto
    -0.88
     jorge
    -0.88
     Perci
    -0.86
     shenan
    -0.85
     Pamph
    -0.84
     sergio
    -0.84
     Dica
    -0.84
    POSITIVE LOGITS
    <bos>
    0.65
    むしろ
    0.51
    逆に
    0.50
     positive
    0.49
     actually
    0.48
    CURLOPT
    0.47
     embrace
    0.46
     positively
    0.46
     creativity
    0.46
     juist
    0.45
    Activations Density 0.427%

    No Known Activations