INDEX

Explanations

assertions or statements of fact about events or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Majefty

-0.79

 ftate

-0.71

 itſelf

-0.70

 ſtate

-0.70

 myſelf

-0.66

 themſelves

-0.66

 Theſe

-0.65

 ſeveral

-0.65

 houſe

-0.63

 poffe

-0.63

POSITIVE LOGITS

 متعلقه

0.87

 محفوظة

0.70

 '\\;'

0.70

SourceChecksum

0.69

his

0.68

 defaultstate

0.59

AsUp

0.57

him

0.57

RTLD

0.56

 مرئيه

0.56

Activations Density 0.216%

assertions or statements of fact about events or situations

No Comments

No Known Activations