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. 453
    Prev
    Next
    INDEX
    Explanations

    themes related to personal stories and experiences, especially those involving challenges, relationships, and significant events

    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
    1967
    +0.13
    0.4%
    50
    +0.12
    0.4%
    453
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1967
    +0.13
    0.06
    111
    +0.12
    0.03
    1395
    +0.11
    0.04
    Negative Logits
     swarovski
    -1.19
     affor
    -1.17
     Mlle
    -1.16
     hairc
    -1.12
     disagre
    -1.11
     impractica
    -1.09
     excru
    -1.09
     scrat
    -1.08
     volunte
    -1.08
     guarante
    -1.08
    POSITIVE LOGITS
     thereof
    0.93
     them
    0.90
     therein
    0.73
     it
    0.72
     thereto
    0.71
    them
    0.69
     آن
    0.61
     him
    0.61
     thereon
    0.59
    之
    0.59
    Activations Density 1.299%

    No Known Activations