INDEX

Explanations

interactive elements and questions in casual conversation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 میتوان

-0.64

 NgModule

-0.62

).\\

-0.61

 vectorielles

-0.59

\$

-0.59

\_

-0.55

\_

-0.55

InjectMocks

-0.55

.\\

-0.55

$\$

-0.54

POSITIVE LOGITS

ur

1.04

0.97

lyk

0.94

tht

0.94

abt

0.93

frm

0.93

urs

0.89

dat

0.80

uve

0.80

nw

0.79

Activations Density 0.198%

interactive elements and questions in casual conversation

No Comments

No Known Activations