INDEX

Explanations

indicators of programming structure or hierarchy, likely within code or documentation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 évi

-0.67

 navideños

-0.66

adpleegd

-0.65

_('

-0.65

mybatisplus

-0.64

 препратки

-0.64

љено

-0.64

ませんが

-0.63

Попис

-0.62

 Powell

-0.61

POSITIVE LOGITS

enumi

0.90

</th>

0.86

 الحره

0.85

</h2>

0.83

 nakalista

0.76

 StatelessWidget

0.75

<tr>

0.73

</i>

0.72

</h6>

0.71

 Audiodateien

0.71

Activations Density 0.058%

indicators of programming structure or hierarchy, likely within code or documentation

No Comments

No Known Activations