INDEX

Explanations

terms related to risks and medical diagnoses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ועוד

-0.58

sowie

-0.55

/,

-0.55

//}

-0.55

and

-0.54

 sendiri

-0.54

 กับ

-0.54

[],

-0.53

以及

-0.53

 และ

-0.53

POSITIVE LOGITS

Datuak

0.74

BufferException

0.69

 AssemblyVersion

0.69

 Zephyr

0.64

 للمعارف

0.64

TargetException

0.63

 affinch

0.61

 EnglishChoose

0.60

 tombs

0.60

Trama

0.60

Activations Density 0.437%

terms related to risks and medical diagnoses

No Comments

No Known Activations