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. 10074
    Prev
    Next
    INDEX
    Explanations

    phrases related to accidents or police incidents

    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
    1150
    +0.16
    0.5%
    2034
    +0.15
    0.4%
    1013
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.16
    0.07
    1499
    +0.15
    0.07
    1997
    +0.12
    0.04
    Negative Logits
     effe
    -1.57
     desir
    -1.56
     swarovski
    -1.45
     perfet
    -1.38
     michelin
    -1.37
     peppa
    -1.36
     nece
    -1.36
     eiffel
    -1.35
     ecru
    -1.35
     scrat
    -1.34
    POSITIVE LOGITS
    .
    0.82
    ;
    0.70
     conducted
    0.66
    。
    0.64
     held
    0.61
    <bos>
    0.60
     involving
    0.60
    .(*
    0.60
    !
    0.59
     carried
    0.59
    Activations Density 0.453%

    No Known Activations