INDEX

Explanations

quantitative attributes related to medical measurements or indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 للاسماء

-0.91

])))

-0.82

contentLoaded

-0.75

})->

-0.74

 utafitiHapana

-0.72

 gyhoeddwyd

-0.71

 trajets

-0.71

})]

-0.68

 externi

-0.68

SourceChecksum

-0.67

POSITIVE LOGITS

AddTagHelper

0.62

 TimeUnit

0.56

schaft

0.56

hdessä

0.51

réhen

0.51

stdc

0.49

kulum

0.49

abancı

0.47

ague

0.47

में

0.46

Activations Density 0.030%

quantitative attributes related to medical measurements or indicators

No Comments

No Known Activations