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. 8370
    Prev
    Next
    INDEX
    Explanations

    phrases related to body image and personal struggles

    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
    +0.16
    0.6%
    1978
    +0.14
    0.5%
    764
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.16
    0.07
    764
    +0.14
    0.04
    1056
    +0.13
    0.05
    Negative Logits
     ivi
    -1.25
     utop
    -1.22
     robus
    -1.21
     dora
    -1.17
     palab
    -1.17
     mef
    -1.16
     ohr
    -1.16
     solidar
    -1.16
     gmbh
    -1.15
     gend
    -1.15
    POSITIVE LOGITS
     alot
    0.70
     withal
    0.67
     definately
    0.61
     Shakspeare
    0.60
     poetical
    0.60
     really
    0.59
     whither
    0.58
    şey
    0.58
     unspeak
    0.57
     very
    0.56
    Activations Density 0.771%

    No Known Activations