INDEX

Explanations

words related to conditions or situations that are not reported, known, or treated

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

+#+#

-0.78

mockMvc

-0.78

Portail

-0.70

={({

-0.69

CardModule

-0.68

IBar

-0.68

RuleContext

-0.66

GenerationType

-0.66

 وتسجيلات

-0.66

gdx

-0.65

POSITIVE LOGITS

 uncin

1.18

UNE

1.01

Uns

0.98

UNA

0.97

unt

0.96

 doubtnut

0.93

Uno

0.93

 undec

0.92

Unt

0.91

 ungu

0.91

Activations Density 0.296%

words related to conditions or situations that are not reported, known, or treated

No Comments

No Known Activations