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. 15604
    Prev
    Next
    INDEX
    Explanations

    descriptions of events happening in a sequence

    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
    1013
    +0.10
    0.3%
    1539
    +0.09
    0.3%
    906
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.10
    0.05
    2003
    +0.09
    0.05
    736
    +0.08
    0.05
    Negative Logits
     hairc
    -0.89
     cushi
    -0.81
     affor
    -0.79
     ecru
    -0.74
     paisley
    -0.72
     gouver
    -0.72
     Cfr
    -0.71
     bandeau
    -0.71
     increa
    -0.69
     embodi
    -0.68
    POSITIVE LOGITS
    StructEnd
    0.83
     afterwards
    0.57
    Obrigado
    0.56
    XmlAccessorType
    0.55
     thanked
    0.53
    Về
    0.53
     afterward
    0.53
    writeFieldEnd
    0.52
     mergeFrom
    0.52
    destroyAll
    0.52
    Activations Density 0.498%

    No Known Activations