© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3792
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports and player evaluations

    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
    599
    +0.11
    0.3%
    1861
    +0.07
    0.2%
    108
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.11
    0.04
    1501
    +0.07
    0.04
    1957
    +0.07
    0.03
    Negative Logits
     fup
    -1.22
     sovere
    -1.21
     Intere
    -1.17
     ftu
    -1.17
     impractica
    -1.14
     fta
    -1.13
     unlaw
    -1.12
     fep
    -1.11
     effe
    -1.11
     wien
    -1.11
    POSITIVE LOGITS
    GOTREF
    0.69
    AndEndTag
    0.65
    InjectMocks
    0.55
    脚注の使い方
    0.55
     ролях
    0.55
     Chwiliwch
    0.53
     AssemblyCompany
    0.53
     team
    0.52
    <bos>
    0.51
    Sqft
    0.51
    Activations Density 0.382%

    No Known Activations