INDEX

Explanations

the presence of initial contextual indicators or markers that imply a new section or topic shift in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

<eos>

-1.25

-0.99

-0.83

 […]

-0.79

-0.78

).

-0.77

↵↵

-0.74

-0.72

<b>

-0.71

']]

-0.67

POSITIVE LOGITS

}{

0.84

onOptions

0.80

 myſelf

0.78

AutoresizingMask

0.74

onViewCreated

0.72

bootstrapcdn

0.71

 photolibrary

0.71

IsContent

0.70

\#

0.69

BeginInit

0.69

Activations Density 0.016%

the presence of initial contextual indicators or markers that imply a new section or topic shift in the text

No Comments

No Known Activations