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. 15148
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly doctors and people mentioned in the text

    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
    1150
    +0.22
    0.7%
    227
    +0.12
    0.4%
    2034
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.22
    0.07
    227
    +0.12
    0.05
    1097
    +0.10
    0.05
    Negative Logits
     increa
    -2.13
     affor
    -2.10
     desir
    -2.09
     inev
    -2.06
     volunte
    -2.04
     unden
    -1.99
     guarante
    -1.99
     fuf
    -1.98
     emphat
    -1.98
     purcha
    -1.97
    POSITIVE LOGITS
    .
    1.15
    ;
    0.97
    。
    0.93
    ).
    0.88
    ,
    0.88
    ."
    0.83
    !
    0.82
    :
    0.81
    .)
    0.81
    );
    0.81
    Activations Density 0.201%

    No Known Activations