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. 148
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or periods leading up to a specific event

    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
    1042
    +0.11
    0.3%
    474
    +0.11
    0.3%
    1035
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.11
    0.05
    1035
    +0.11
    0.04
    1999
    +0.08
    0.04
    Negative Logits
     heapq
    -0.60
     Décembre
    -0.53
     trozos
    -0.53
    OGND
    -0.51
    )\}
    -0.50
     afla
    -0.50
    ellemző
    -0.50
     martie
    -0.49
     pymysql
    -0.49
    onActivityResult
    -0.48
    POSITIVE LOGITS
     Verk
    0.73
     coö
    0.70
     reluct
    0.68
     imago
    0.67
     pessi
    0.67
     pamph
    0.67
     sophistic
    0.66
     maer
    0.65
     apprehen
    0.65
     emphat
    0.65
    Activations Density 0.177%

    No Known Activations