INDEX

Explanations

references to post-event sequences or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

mybatisplus

-0.83

 فريبيس

-0.82

+#+

-0.80

errHandler

-0.80

 greateſt

-0.78

 Majefty

-0.77

Efq

-0.76

 kaarangay

-0.76

 preſent

-0.75

antMatchers

-0.73

POSITIVE LOGITS

After

0.77

 after

0.76

 despite

0.68

 After

0.68

Despite

0.67

 Considering

0.67

Considering

0.66

 because

0.66

 nadat

0.63

due

0.63

Activations Density 0.088%

references to post-event sequences or conditions

No Comments

No Known Activations