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. 15569
    Prev
    Next
    INDEX
    Explanations

    text related to technical issues and bug tracking within a system

    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
    2030
    +0.11
    0.3%
    453
    +0.11
    0.3%
    1077
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.11
    0.04
    1241
    +0.11
    0.03
    1471
    +0.10
    0.03
    Negative Logits
     fta
    -2.58
     shenan
    -2.56
     disagre
    -2.47
     emphat
    -2.46
     reluct
    -2.46
     increa
    -2.44
     accla
    -2.42
     volunte
    -2.40
     depic
    -2.38
     maneu
    -2.38
    POSITIVE LOGITS
     by
    0.82
     CURLOPT
    0.74
    by
    0.74
     durch
    0.74
    izr
    0.71
    titleMargin
    0.70
     pelo
    0.69
    GIH
    0.69
     BoxFit
    0.68
    TextHelper
    0.68
    Activations Density 0.144%

    No Known Activations