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. 8297
    Prev
    Next
    INDEX
    Explanations

    potential threats in social situations, particularly related to strangers in specific settings like bars

    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
    776
    +0.10
    0.3%
    198
    +0.09
    0.3%
    906
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.10
    0.06
    1579
    +0.09
    0.04
    1825
    +0.09
    0.03
    Negative Logits
     ecru
    -0.72
     hairc
    -0.71
     swarovski
    -0.71
     cushi
    -0.69
     ineffec
    -0.66
     lamborghini
    -0.66
     silken
    -0.64
     Whence
    -0.64
     tupperware
    -0.63
     disagre
    -0.63
    POSITIVE LOGITS
     suspiciously
    0.64
     suddenly
    0.61
     suspicious
    0.60
     signs
    0.56
     odd
    0.55
     strange
    0.55
     unusually
    0.53
     sudden
    0.52
    LookAnd
    0.52
     strangely
    0.50
    Activations Density 0.760%

    No Known Activations