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. 761
    Prev
    Next
    INDEX
    Explanations

    words related to strength and power or physical characteristics

    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
    1013
    +0.10
    0.3%
    655
    +0.09
    0.3%
    468
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.10
    0.07
    468
    +0.09
    0.06
    942
    +0.09
    0.07
    Negative Logits
     solidar
    -1.25
     ideolog
    -1.24
     robus
    -1.23
     dises
    -1.18
     utop
    -1.15
     ?...
    -1.13
     apparti
    -1.13
     !...
    -1.13
     sappi
    -1.12
     kram
    -1.11
    POSITIVE LOGITS
     enough
    0.73
    .
    0.59
     in
    0.59
     genug
    0.59
     everywhere
    0.58
     again
    0.58
    <bos>
    0.57
     by
    0.57
    ;
    0.57
    !
    0.57
    Activations Density 0.497%

    No Known Activations