© 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. 2302
    Prev
    Next
    INDEX
    Explanations

    personal possessive pronouns indicating ownership

    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
    1635
    +0.08
    0.2%
    1265
    +0.07
    0.2%
    1926
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1635
    +0.08
    0.02
    1786
    +0.07
    0.02
    282
    +0.06
    0.02
    Negative Logits
     my
    -0.81
    my
    -0.76
     My
    -0.72
    define
    -0.69
    My
    -0.69
     me
    -0.68
    EndContext
    -0.68
    BUYER
    -0.67
     I
    -0.67
    lang
    -0.66
    POSITIVE LOGITS
     shenan
    1.94
     Yours
    1.88
     maneu
    1.85
     accla
    1.84
     excru
    1.80
     disagre
    1.79
     lidl
    1.78
     yours
    1.77
     stockholm
    1.75
     affor
    1.75
    Activations Density 0.066%

    No Known Activations