© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1003
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to potential negative outcomes or worst-case scenarios

    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
    394
    +0.28
    1.1%
    599
    +0.14
    0.5%
    872
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.28
    0.09
    764
    +0.14
    0.10
    1415
    +0.12
    0.03
    Negative Logits
     ?...
    -0.94
    :,,
    -0.90
     !...
    -0.90
     emphat
    -0.86
     fuf
    -0.85
     hentai
    -0.84
    Yess
    -0.82
     accla
    -0.82
     »>
    -0.81
    Wut
    -0.81
    POSITIVE LOGITS
     disambiguazione
    0.56
     useAppContext
    0.48
    WindowConstants
    0.48
    vocable
    0.46
    writeFieldEnd
    0.45
    IVEREF
    0.44
    roasted
    0.43
     actually
    0.42
    vellous
    0.41
     yourself
    0.40
    Activations Density 4.998%

    No Known Activations