INDEX

Explanations

mentions of the word "leg" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Latch

-0.56

 UIFont

-0.56

Portale

-0.52

 BoxDecoration

-0.52

 AdapterView

-0.52

 Paglinawan

-0.51

webElement

-0.50

azón

-0.50

ährend

-0.50

juegos

-0.50

POSITIVE LOGITS

ك

0.69

findpost

0.69

uxxxx

0.63

loride

0.61

StoryboardSegue

0.59

Prefer

0.58

ContentAsync

0.58

 arşivlendi

0.57

ک

0.57

InBackground

0.57

Activations Density 0.111%

mentions of the word "leg" in various contexts

No Comments

No Known Activations