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. 1775
    Prev
    Next
    INDEX
    Explanations

    information related to personal stories and achievements

    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
    227
    +0.16
    0.5%
    381
    +0.16
    0.5%
    184
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.16
    0.06
    513
    +0.16
    0.03
    353
    +0.13
    0.03
    Negative Logits
     indeb
    -1.00
     citta
    -0.91
     gymnas
    -0.89
     Energi
    -0.86
     uefa
    -0.85
     daf
    -0.84
     ordina
    -0.83
     RSSSF
    -0.82
     combusti
    -0.82
     gmbh
    -0.81
    POSITIVE LOGITS
     unspeak
    1.14
     intersper
    1.07
     apprehen
    1.05
     shenan
    1.00
     felicity
    0.94
    <bos>
    0.91
     earnestness
    0.89
     pretensions
    0.89
     vainly
    0.89
     disagre
    0.88
    Activations Density 0.450%

    No Known Activations