© 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. 2512
    Prev
    Next
    INDEX
    Explanations

    references to stairs

    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
    1705
    +0.09
    0.3%
    1480
    +0.08
    0.3%
    1328
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.09
    0.02
    690
    +0.08
    0.03
    416
    +0.08
    0.02
    Negative Logits
    <bos>
    -0.86
    ുറ
    -0.67
    WriteLiteral
    -0.63
    RuleContext
    -0.61
     EconPapers
    -0.60
    public
    -0.60
     nh
    -0.59
    xase
    -0.58
    投
    -0.58
    ੰ
    -0.58
    POSITIVE LOGITS
     Stairs
    1.90
     stairs
    1.89
     excru
    1.75
     wherea
    1.73
     increa
    1.73
     reluct
    1.73
     stair
    1.72
     erad
    1.71
     inev
    1.68
     stairway
    1.66
    Activations Density 0.145%

    No Known Activations