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. 13508
    Prev
    Next
    INDEX
    Explanations

    references to a specific news organization, ABC News, and related terms

    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
    1741
    +0.14
    0.5%
    61
    +0.14
    0.5%
    1222
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.14
    0.02
    650
    +0.14
    0.02
    420
    +0.13
    0.02
    Negative Logits
    Datuak
    -0.68
    Tikang
    -0.54
     willows
    -0.51
     linden
    -0.51
    GenerationType
    -0.51
     conifers
    -0.47
     ingrat
    -0.47
     boughs
    -0.46
    wurde
    -0.46
     solemnity
    -0.46
    POSITIVE LOGITS
     ABC
    1.38
    ABC
    1.29
     abc
    1.01
    abc
    1.00
    Abc
    0.79
     ekos
    0.76
     Kategor
    0.71
     konserv
    0.70
     alkoh
    0.68
     akut
    0.68
    Activations Density 0.055%

    No Known Activations