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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 712
    Prev
    Next
    INDEX
    Explanations

    descriptions of medical procedures and conditions, particularly related to surgery and recovery

    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
    856
    +0.15
    0.5%
    1013
    +0.14
    0.5%
    509
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.15
    0.04
    612
    +0.14
    0.00
    1533
    +0.12
    0.01
    Negative Logits
     milano
    -1.45
     mef
    -1.41
     fta
    -1.38
     wien
    -1.38
     hcm
    -1.37
     uniqu
    -1.37
     „,
    -1.36
     napoli
    -1.36
     squa
    -1.35
     ?...
    -1.33
    POSITIVE LOGITS
    astéro
    0.76
     again
    0.73
    Fácil
    0.68
    GRANTED
    0.68
    pyplot
    0.68
    Τι
    0.66
    removeAttr
    0.66
    Bardzo
    0.65
    asteroide
    0.65
    InputTagHelper
    0.64
    Activations Density 0.151%

    No Known Activations