INDEX

Explanations

phrases indicating the inclusion or existence of something within a set or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 "..\..\

-0.57

Uint

-0.57

 ResourceManager

-0.57

 baili

-0.54

tidig

-0.53

 zdrowia

-0.51

 yüzden

-0.51

dimer

-0.50

 bill

-0.47

POSITIVE LOGITS

 CONTAIN

1.05

 contain

1.02

 Contain

0.93

contain

0.92

)}</

0.88

 contained

0.87

 ―――――

0.86

RenderAtEndOf

0.84

 contener

0.83

 ――――――――

0.82

Activations Density 0.156%

phrases indicating the inclusion or existence of something within a set or context

No Comments

No Known Activations