Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5659
    Prev
    Next
    INDEX
    Explanations

    terms related to the action of "mounting" something

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.13
    0.8%
    200
    +0.11
    0.6%
    663
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.13
    0.03
    78
    +0.11
    0.02
    663
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.67
    ⓧ
    -0.88
     AssemblyCompany
    -0.63
    PyExc
    -0.62
     inform
    -0.62
    opsida
    -0.61
    🎰
    -0.60
    asp
    -0.59
    bewerken
    -0.58
     resourceCulture
    -0.58
    POSITIVE LOGITS
     milf
    1.53
     Mounts
    1.46
     pixar
    1.41
     depic
    1.38
     maneu
    1.37
     madonna
    1.35
     affor
    1.35
     wattpad
    1.35
     ecru
    1.35
     MOUNT
    1.35
    Activations Density 0.125%

    No Known Activations