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. 122
    Prev
    Next
    INDEX
    Explanations

    percentage values and measurement units

    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
    1343
    +0.13
    0.4%
    1978
    +0.12
    0.4%
    776
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.13
    0.05
    776
    +0.12
    0.04
    1471
    +0.12
    0.04
    Negative Logits
     volunte
    -1.03
    Autoritní
    -1.01
     viciss
    -0.92
     thut
    -0.92
     hecta
    -0.91
    fordable
    -0.89
     wherea
    -0.89
     „,
    -0.88
     venezuela
    -0.88
     fte
    -0.87
    POSITIVE LOGITS
    Matchers
    0.51
     same
    0.49
    2
    0.48
    GOTREF
    0.48
     확인함
    0.47
     again
    0.47
    8
    0.46
    Dimensiones
    0.46
    KURZBESCHREIBUNG
    0.45
    HttpPut
    0.45
    Activations Density 0.141%

    No Known Activations