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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10554
    Prev
    Next
    INDEX
    Explanations

    mentions of business deals falling through or being blocked

    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
    1499
    +0.09
    0.3%
    604
    +0.09
    0.3%
    1120
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.09
    0.06
    213
    +0.09
    0.05
    180
    +0.09
    0.05
    Negative Logits
     indestru
    -1.23
     inconce
    -1.21
     impra
    -1.17
     indescri
    -1.17
     intersper
    -1.15
     emphat
    -1.14
     increa
    -1.13
     disagre
    -1.12
     !...
    -1.09
     milf
    -1.07
    POSITIVE LOGITS
     approval
    0.88
     approvals
    0.82
    approval
    0.77
     Approval
    0.65
     typelib
    0.64
    Välislingid
    0.61
    Approval
    0.61
     approved
    0.59
     approve
    0.59
    RenderAtEndOf
    0.59
    Activations Density 0.501%

    No Known Activations