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. 2716
    Prev
    Next
    INDEX
    Explanations

    webpage instructions and descriptions

    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
    605
    +0.10
    0.3%
    136
    +0.09
    0.3%
    453
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    518
    +0.10
    0.02
    772
    +0.09
    0.02
    1346
    +0.09
    0.01
    Negative Logits
     fta
    -1.64
     increa
    -1.57
     volunte
    -1.53
     maneu
    -1.51
     affor
    -1.51
     ftu
    -1.51
     encomp
    -1.49
     fte
    -1.46
     depic
    -1.46
     guarante
    -1.45
    POSITIVE LOGITS
     his
    1.08
     their
    1.02
    his
    1.02
    their
    1.00
     its
    0.97
     your
    0.93
     her
    0.91
     our
    0.87
     my
    0.85
    its
    0.84
    Activations Density 0.111%

    No Known Activations