INDEX

Explanations

phrases signaling the beginning of a new paragraph or section

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

$.

-1.12

 doubtnut

-1.04

 MainAxisSize

-1.04

BibitemShut

-1.03

 lenker

-1.00

 ་་

-1.00

 Roskov

-0.98

 виправивши

-0.98

AnimationsModule

-0.96

IndentedString

-0.94

POSITIVE LOGITS

For

1.87

For

1.83

FOR

1.39

FOR

1.30

for

1.30

To

0.92

for

0.92

 Für

0.87

 Для

0.87

ForAll

0.84

Activations Density 0.118%

phrases signaling the beginning of a new paragraph or section

No Comments

No Known Activations