INDEX

Explanations

terms related to clinical contexts or studies

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

 للمعارف

-0.83

antMatchers

-0.64

 AssemblyCulture

-0.61

NameInMap

-0.57

[*]

-0.56

 eorum

-0.56

 виправивши

-0.54

 gynhyrchwyd

-0.54

XmlAccessorType

-0.53

expandindo

-0.53

POSITIVE LOGITS

 trials

0.76

帖最后由

0.71

trials

0.68

 trial

0.67

Trials

0.64

 "));

0.60

 jugement

0.59

trial

0.59

 practice

0.58

")

0.55

Activations Density 0.168%

terms related to clinical contexts or studies

No Comments

No Known Activations