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. 16071
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations

    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
    +0.13
    0.5%
    897
    +0.13
    0.5%
    1805
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.13
    0.02
    1805
    +0.13
    0.02
    897
    +0.12
    0.02
    Negative Logits
    LabelTagHelper
    -0.63
    BeNil
    -0.57
    CompleteListener
    -0.55
    ModelForm
    -0.54
    ();)
    -0.53
    DataPropertyName
    -0.51
    })));
    -0.51
    sendStatus
    -0.50
    Embeddable
    -0.49
    ("/:
    -0.49
    POSITIVE LOGITS
     Eastern
    1.26
    Eastern
    1.14
     EASTERN
    1.05
     eastern
    1.00
    eastern
    0.91
     easter
    0.82
     East
    0.80
     Lázaro
    0.77
     Dica
    0.76
     Marín
    0.76
    Activations Density 0.037%

    No Known Activations