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. 13812
    Prev
    Next
    INDEX
    Explanations

    words related to controversial or attention-grabbing topics

    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
    1553
    +0.14
    0.4%
    1013
    +0.14
    0.4%
    1978
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.14
    0.10
    1013
    +0.14
    0.09
    284
    +0.09
    0.08
    Negative Logits
     Okt
    -1.17
     kram
    -1.10
     uhr
    -1.08
     reputa
    -1.08
     logis
    -1.07
     priva
    -1.07
     beren
    -1.07
     palet
    -1.07
     frans
    -1.07
     meis
    -1.06
    POSITIVE LOGITS
     instead
    0.69
     while
    0.68
     during
    0.66
     or
    0.65
     indoors
    0.63
     and
    0.60
     whilst
    0.59
     Cæsar
    0.58
     without
    0.57
     incessantly
    0.56
    Activations Density 0.719%

    No Known Activations