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. 8205
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns denoting ownership or connection to someone or something

    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
    1385
    +0.15
    0.5%
    1741
    +0.10
    0.3%
    1978
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1317
    +0.15
    0.05
    817
    +0.10
    0.03
    1937
    +0.10
    0.04
    Negative Logits
     reluct
    -1.90
     snoopy
    -1.88
     milf
    -1.88
     impra
    -1.87
     affor
    -1.86
     scrat
    -1.86
     increa
    -1.85
     shenan
    -1.82
     disagre
    -1.82
     unspeak
    -1.80
    POSITIVE LOGITS
    windowFixed
    0.73
    يميديا
    0.72
     insuffisamment
    0.71
    RTSC
    0.66
    <bos>
    0.65
    URLException
    0.63
     chest
    0.63
    Nº
    0.61
    HostException
    0.60
    ждународ
    0.60
    Activations Density 0.213%

    No Known Activations