© 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. 14077
    Prev
    Next
    INDEX
    Explanations

    words related to the effects of various actions or treatments

    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
    1896
    +0.13
    0.5%
    25
    +0.12
    0.5%
    1437
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    990
    +0.13
    0.04
    1437
    +0.12
    0.03
    1133
    +0.12
    0.03
    Negative Logits
     Bolívar
    -0.50
     meras
    -0.48
     lã
    -0.48
    Ծանոթ
    -0.47
    Leia
    -0.47
    issau
    -0.47
     AssemblyProduct
    -0.46
     aspira
    -0.46
     pstmt
    -0.45
     interro
    -0.45
    POSITIVE LOGITS
    effect
    1.18
     effects
    1.18
     effect
    1.16
     Effect
    1.15
     Effects
    1.13
    Effect
    1.11
    effects
    1.10
    Effects
    1.06
     effets
    1.03
     EFFECTS
    1.03
    Activations Density 0.068%

    No Known Activations