Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14034
    Prev
    Next
    INDEX
    Explanations

    positive mentions or sentiments towards people, events, or actions

    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
    674
    +0.09
    0.3%
    555
    +0.08
    0.2%
    1445
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1677
    +0.09
    0.06
    1507
    +0.08
    0.04
    1276
    +0.08
    0.05
    Negative Logits
     Añ
    -0.65
     sappi
    -0.65
     dichi
    -0.64
     masaj
    -0.62
     surfact
    -0.60
     Áng
    -0.60
     khong
    -0.59
     apparti
    -0.59
     aquare
    -0.58
     utop
    -0.57
    POSITIVE LOGITS
     unspeak
    1.06
     tolerably
    1.02
     gaily
    0.97
     intrigu
    0.96
     nobly
    0.96
     apprehen
    0.95
     vainly
    0.92
     endeavouring
    0.92
     reconno
    0.91
     plenti
    0.90
    Activations Density 0.238%

    No Known Activations