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. 3012
    Prev
    Next
    INDEX
    Explanations

    phrases related to writing or inventing stories and documents, sometimes in a critical or speculative context

    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
    1147
    +0.07
    0.2%
    967
    +0.07
    0.2%
    151
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1958
    +0.07
    0.04
    1513
    +0.07
    0.01
    1273
    +0.07
    0.03
    Negative Logits
     increa
    -1.09
     affor
    -1.07
     purcha
    -1.06
     michelin
    -1.02
     coö
    -1.02
     unden
    -1.02
     guarante
    -1.02
     impra
    -1.02
     alre
    -1.01
     wherea
    -1.01
    POSITIVE LOGITS
     resort
    0.82
     resorted
    0.74
     instead
    0.70
     rely
    0.70
     resorts
    0.67
     alternative
    0.66
    Instead
    0.65
     alternatives
    0.64
     resorting
    0.63
     Instead
    0.63
    Activations Density 0.429%

    No Known Activations