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. 15758
    Prev
    Next
    INDEX
    Explanations

    mentions of interviews

    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
    1023
    +0.14
    0.5%
    805
    +0.13
    0.4%
    1520
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1023
    +0.14
    0.04
    805
    +0.13
    0.03
    1520
    +0.11
    0.03
    Negative Logits
     autunno
    -0.73
     balenciaga
    -0.69
     fendi
    -0.67
     Giugno
    -0.65
     ognuno
    -0.63
     Luglio
    -0.63
     automne
    -0.61
     prenota
    -0.60
     canin
    -0.59
     affez
    -0.59
    POSITIVE LOGITS
     interview
    1.47
     interviews
    1.32
     Interview
    1.31
    interview
    1.28
    Interview
    1.25
     interviewing
    1.19
    Interviews
    1.10
     Interviews
    1.10
     interviewed
    1.10
     interviewer
    1.07
    Activations Density 0.083%

    No Known Activations