INDEX

Explanations

specific medical and biological terms related to conditions, responses, and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

に

-0.98

ly

-0.85

 Landis

-0.82

gnügen

-0.79

 moeite

-0.78

 Halen

-0.78

ik

-0.75

 Enid

-0.75

 suivie

-0.75

Michele

-0.75

POSITIVE LOGITS

й

1.14

一个

0.91

йки

0.87

__*/

0.87

 Bartol

0.86

 Pamp

0.85

 Garr

0.84

OTT

0.84

BBM

0.84

 Hamp

0.83

Activations Density 3.538%

specific medical and biological terms related to conditions, responses, and measurements

No Comments

No Known Activations