© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13844
    Prev
    Next
    INDEX
    Explanations

    words related to technical computer activities like logging in, registering, and managing accounts

    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
    1276
    +0.09
    0.3%
    946
    +0.08
    0.2%
    120
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.09
    0.02
    946
    +0.08
    0.02
    482
    +0.08
    0.02
    Negative Logits
     userModel
    -0.73
     ApiService
    -0.64
     getCategory
    -0.58
    userRole
    -0.56
     getCity
    -0.55
     Obtener
    -0.54
     getCustomer
    -0.54
     romero
    -0.53
     rir
    -0.52
     Conexion
    -0.51
    POSITIVE LOGITS
     login
    1.09
     Login
    1.01
    login
    0.94
    Login
    0.86
    LOGIN
    0.80
     LOGIN
    0.70
     username
    0.70
     Ename
    0.68
     logout
    0.63
    登录
    0.61
    Activations Density 0.100%

    No Known Activations