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. 15712
    Prev
    Next
    INDEX
    Explanations

    mentions of negative attributes or accusations in a document

    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
    1403
    +0.11
    0.3%
    1965
    +0.09
    0.3%
    1992
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1992
    +0.11
    0.05
    1965
    +0.09
    0.06
    1287
    +0.08
    0.05
    Negative Logits
     Juf
    -2.12
     Keny
    -2.00
     accla
    -1.88
     Intere
    -1.79
     reluct
    -1.79
     Khart
    -1.79
     intersper
    -1.72
     Augu
    -1.70
     encomp
    -1.67
     Malte
    -1.67
    POSITIVE LOGITS
     goes
    0.85
     şeyi
    0.84
    SequentialGroup
    0.83
     seems
    0.82
     went
    0.81
    awtextra
    0.81
     is
    0.81
     isn
    0.81
     was
    0.79
     dlaczego
    0.78
    Activations Density 0.398%

    No Known Activations