INDEX

Explanations

terms related to medical conditions, particularly those associated with brain and cognitive functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Datuak

-0.66

jsxFileName

-0.64

UnknownFieldSet

-0.59

ternut

-0.59

onAttach

-0.58

ỡng

-0.53

رشف

-0.51

escent

-0.51

تقاوى

-0.51

ymce

-0.50

POSITIVE LOGITS

以外にも

0.61

 yanı

0.58

はもちろん

0.57

 مشين

0.56

 lisäksi

0.56

をはじめ

0.55

を中心

0.54

 alone

0.52

 ovviamente

0.50

 obviamente

0.50

Activations Density 0.496%

terms related to medical conditions, particularly those associated with brain and cognitive functions

No Comments

No Known Activations