INDEX

Explanations

terms related to legal and scientific investigative contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

providedIn

-0.67

-0.63

-0.62

ج

-0.62

-0.61

Slf

-0.60

-0.59

moveToFirst

-0.59

POSITIVE LOGITS

 myſelf

0.98

 themſelves

0.98

 doubtnut

0.96

 whoſe

0.89

 himſelf

0.87

 itſelf

0.84

 ―――――

0.80

Efq

0.79

 juſt

0.78

 fometimes

0.77

Activations Density 2.240%

terms related to legal and scientific investigative contexts

No Comments

No Known Activations