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. 7913
    Prev
    Next
    INDEX
    Explanations

    mentions of podcasts, podcast episodes, and podcasters

    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
    938
    +0.13
    0.5%
    395
    +0.13
    0.5%
    568
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.13
    0.02
    395
    +0.13
    0.02
    938
    +0.12
    0.02
    Negative Logits
     NKC
    -0.60
    InjectAttribute
    -0.58
    Več
    -0.54
    Conheça
    -0.53
     Akismet
    -0.53
     يتيمه
    -0.53
    ríamos
    -0.51
    Iné
    -0.51
     ἔ
    -0.50
    XmlAccessType
    -0.50
    POSITIVE LOGITS
     Pod
    1.42
     pod
    1.42
    Pod
    1.36
     podcast
    1.36
    pod
    1.32
     pods
    1.22
     podcasts
    1.20
     Podcast
    1.19
     POD
    1.13
    podcast
    1.12
    Activations Density 0.078%

    No Known Activations