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. 1627
    Prev
    Next
    INDEX
    Explanations

    expressions indicating permanence or frequency

    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
    1363
    +0.13
    0.4%
    1334
    +0.12
    0.4%
    120
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1480
    +0.13
    0.04
    1092
    +0.12
    0.04
    1334
    +0.11
    0.04
    Negative Logits
     alberto
    -0.68
     bangkok
    -0.67
     Quod
    -0.66
     kani
    -0.65
     ikat
    -0.64
     andrea
    -0.64
     Cfr
    -0.63
     Epif
    -0.63
     guma
    -0.63
     baka
    -0.63
    POSITIVE LOGITS
     ALWAYS
    1.09
     always
    1.09
    Always
    1.04
    always
    1.03
     Always
    1.02
    ALWAYS
    1.01
    deauna
    0.90
    <bos>
    0.86
     alway
    0.83
     siempre
    0.83
    Activations Density 0.185%

    No Known Activations