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. 627
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal activities, specifically robbery

    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
    1622
    +0.11
    0.3%
    990
    +0.10
    0.3%
    1013
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1622
    +0.11
    0.02
    976
    +0.10
    0.03
    1437
    +0.09
    0.03
    Negative Logits
     fup
    -1.18
     effe
    -1.18
     dispen
    -1.15
     guarante
    -1.13
     volunte
    -1.13
     michelin
    -1.13
     vogli
    -1.11
     autob
    -1.10
     lidl
    -1.10
     voleva
    -1.08
    POSITIVE LOGITS
     robbery
    1.03
     robberies
    0.85
     robbed
    0.77
     theft
    0.75
     robbers
    0.75
     Robbery
    0.74
     robbing
    0.70
     heist
    0.68
     steals
    0.68
     burglary
    0.67
    Activations Density 0.159%

    No Known Activations