© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1324
    Prev
    Next
    INDEX
    Explanations

    information related to Autumn/Fall season facts and folklore

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    823
    +0.09
    0.3%
    678
    +0.07
    0.3%
    2000
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    823
    +0.09
    0.08
    304
    +0.07
    0.04
    283
    +0.07
    0.02
    Negative Logits
    .
    -1.27
     have
    -1.27
    ,
    -1.27
     will
    -1.25
     had
    -1.25
     are
    -1.25
     then
    -1.25
     and
    -1.24
     also
    -1.24
     on
    -1.24
    POSITIVE LOGITS
     aen
    3.48
     fta
    3.37
     mef
    3.36
     fto
    3.35
     fte
    3.35
     effe
    3.34
     squa
    3.34
     stockholm
    3.34
     wien
    3.29
     blos
    3.29
    Activations Density 0.381%

    No Known Activations