© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6574
    Prev
    Next
    INDEX
    Explanations

    references to a specific name "Howard"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1961
    +0.16
    0.9%
    971
    +0.16
    0.9%
    1276
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.16
    0.04
    1256
    +0.16
    0.03
    1276
    +0.15
    0.03
    Negative Logits
    <bos>
    -1.30
    více
    -0.58
    mtable
    -0.57
    ==""){
    -0.51
    glDisable
    -0.51
    Galerie
    -0.48
    Архівовано
    -0.48
    VIAF
    -0.48
     BioLib
    -0.48
    Бан
    -0.47
    POSITIVE LOGITS
     Howard
    1.81
    Howard
    1.73
     HOWARD
    1.60
     Võ
    0.75
    öyle
    0.74
     Howie
    0.71
     pymysql
    0.71
     liberality
    0.69
     pylab
    0.68
     Portail
    0.67
    Activations Density 0.388%

    No Known Activations