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. 15707
    Prev
    Next
    INDEX
    Explanations

    information related to large-scale economic activities and financial circumstances

    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
    453
    +0.17
    0.6%
    1967
    +0.17
    0.6%
    1870
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    523
    +0.17
    0.05
    757
    +0.17
    0.07
    297
    +0.13
    0.06
    Negative Logits
     unspeak
    -1.13
     indescri
    -1.09
     horrend
    -1.05
     pooh
    -0.99
     unavoid
    -0.98
     intersper
    -0.96
     laug
    -0.95
     downvotes
    -0.93
     unbear
    -0.92
     downvote
    -0.92
    POSITIVE LOGITS
     alkoh
    1.51
     solidar
    1.48
     antik
    1.46
     keramik
    1.39
     kosme
    1.39
     silikon
    1.38
     utop
    1.32
     praktik
    1.29
     ideolog
    1.28
     kram
    1.27
    Activations Density 0.303%

    No Known Activations