INDEX

Explanations

specific references to statistics, conditions, or factors related to health and medical scenarios

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

 متعلقه

-0.85

 lira

-0.61

hilation

-0.60

′,

-0.60

parsedMessage

-0.59

طلحات

-0.58

noons

-0.57

ூர்

-0.56

}$

-0.56

 iArr

-0.56

POSITIVE LOGITS

<bos>

0.89

Autoritní

0.77



0.75

 مرئيه

0.72

Билгалдахарш

0.71

تقاوى

0.69

medriver

0.61

sizeCache

0.60

 mør

0.60

 EconPapers

0.56

Activations Density 0.433%

specific references to statistics, conditions, or factors related to health and medical scenarios

No Comments

No Known Activations