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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 247
    Prev
    Next
    INDEX
    Explanations

    negative emotions and personal experiences

    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
    2034
    +0.10
    0.3%
    964
    +0.09
    0.3%
    1533
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1154
    +0.10
    0.06
    382
    +0.09
    0.06
    1445
    +0.09
    0.07
    Negative Logits
     uncin
    -1.38
     conspic
    -1.37
     eyel
    -1.34
     disreg
    -1.31
     cabrio
    -1.30
     inev
    -1.27
     uniqu
    -1.27
     casio
    -1.25
     vespa
    -1.24
     blos
    -1.24
    POSITIVE LOGITS
     Especially
    0.77
     It
    0.76
     I
    0.70
     Just
    0.65
     But
    0.65
    Especially
    0.64
     especially
    0.64
     Even
    0.63
     Having
    0.63
     Like
    0.63
    Activations Density 0.523%

    No Known Activations