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. 466
    Prev
    Next
    INDEX
    Explanations

    instances of mistrust and skepticism towards certain individuals or entities

    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
    488
    +0.08
    0.2%
    1882
    +0.07
    0.2%
    344
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.08
    0.04
    1882
    +0.07
    0.04
    1111
    +0.07
    0.03
    Negative Logits
     disagre
    -1.42
     maneu
    -1.40
     fortn
    -1.37
     reluct
    -1.36
    «<
    -1.36
     ftu
    -1.36
     pamph
    -1.36
     fta
    -1.35
     affor
    -1.34
     apprehen
    -1.34
    POSITIVE LOGITS
     reliability
    0.83
     Paglinawan
    0.80
     trustworthy
    0.74
     trustworthiness
    0.74
    @[+][
    0.74
    AnchorStyles
    0.73
    ISupport
    0.72
    StoryboardSegue
    0.72
    integrity
    0.72
    Sqft
    0.71
    Activations Density 0.338%

    No Known Activations