© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7673
    Prev
    Next
    INDEX
    Explanations

    business-related terms and phrases

    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
    227
    +0.17
    0.5%
    1870
    +0.09
    0.3%
    959
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    959
    +0.17
    0.05
    227
    +0.09
    0.07
    284
    +0.08
    0.06
    Negative Logits
     guarante
    -1.20
     coö
    -1.12
     ?...
    -1.12
     inev
    -1.06
     fuf
    -1.06
     »>
    -1.06
     effe
    -1.05
     unlaw
    -1.04
     increa
    -1.02
     purcha
    -1.02
    POSITIVE LOGITS
     alongside
    0.63
     while
    0.60
     along
    0.56
    AfterEach
    0.54
     together
    0.54
    while
    0.53
    GrantedAuthority
    0.52
     pinulongan
    0.51
     whereas
    0.51
     until
    0.50
    Activations Density 0.526%

    No Known Activations