© 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. 13807
    Prev
    Next
    INDEX
    Explanations

    information related to travel

    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
    752
    +0.15
    0.5%
    50
    +0.12
    0.4%
    1334
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.15
    0.06
    395
    +0.12
    0.05
    161
    +0.12
    0.04
    Negative Logits
     móg
    -0.76
    OfYear
    -0.66
     będę
    -0.63
    ECTION
    -0.60
     proszę
    -0.58
     wiem
    -0.58
    ecuted
    -0.58
     widać
    -0.58
     zrobi
    -0.58
    ECONDS
    -0.58
    POSITIVE LOGITS
     Souha
    1.13
     Bartholo
    1.11
     Juf
    1.05
     présidenti
    0.98
     simplif
    0.94
     Kün
    0.93
     Membre
    0.93
     Chá
    0.92
     Punj
    0.91
     Keny
    0.91
    Activations Density 0.218%

    No Known Activations