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. 15325
    Prev
    Next
    INDEX
    Explanations

    phrases related to concealing identity and leading back to someone

    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
    946
    +0.11
    0.3%
    198
    +0.10
    0.3%
    876
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.11
    0.04
    1673
    +0.10
    0.02
    1463
    +0.08
    0.04
    Negative Logits
     kosme
    -0.70
     quæ
    -0.67
     Sén
    -0.67
     minimalis
    -0.67
     akut
    -0.65
     panik
    -0.63
     konserv
    -0.63
     kapital
    -0.63
     Cfr
    -0.62
     antik
    -0.62
    POSITIVE LOGITS
     identification
    0.76
     identify
    0.70
     identifying
    0.70
     Identifying
    0.66
     Identification
    0.66
     identifier
    0.65
    identify
    0.64
    Identifying
    0.64
     traceability
    0.62
     Identify
    0.61
    Activations Density 0.379%

    No Known Activations