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. 2755
    Prev
    Next
    INDEX
    Explanations

    phrases related to projects, responses to criticism, and studies or investigations

    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
    1967
    +0.20
    0.7%
    674
    +0.16
    0.5%
    2034
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.20
    0.03
    1678
    +0.16
    0.03
    1967
    +0.13
    0.03
    Negative Logits
     fta
    -1.75
     ftu
    -1.75
     aen
    -1.72
     sovere
    -1.63
     ftre
    -1.61
     tranf
    -1.61
     squa
    -1.61
     perfon
    -1.60
     fup
    -1.58
     thut
    -1.58
    POSITIVE LOGITS
    ?.
    0.78
    s
    0.77
     .
    0.76
     (
    0.73
    .
    0.70
    ။
    0.70
     and
    0.68
    ().
    0.68
    }.
    0.68
    .,
    0.67
    Activations Density 0.161%

    No Known Activations