© 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 EvalsExportsAPI 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. 10813
    Prev
    Next
    INDEX
    Explanations

    words related to movie sequels and the possibility of them happening

    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
    674
    +0.11
    0.3%
    599
    +0.10
    0.3%
    872
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.11
    0.06
    1801
    +0.10
    0.02
    429
    +0.10
    0.03
    Negative Logits
     stockholm
    -1.25
     lidl
    -1.21
     unlaw
    -1.17
     anhyd
    -1.14
     lyon
    -1.11
     Gorb
    -1.11
     Juf
    -1.10
     friable
    -1.09
     unce
    -1.09
     frankfurt
    -1.09
    POSITIVE LOGITS
    <bos>
    0.63
     [
    0.61
     We
    0.55
     we
    0.54
     fans
    0.53
    学科
    0.53
     audiences
    0.52
     ['
    0.51
     concept
    0.51
     excited
    0.51
    Activations Density 0.377%

    No Known Activations