INDEX

Explanations

ellipsis and related punctuation indicating pauses or omissions in speech or writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 myſelf

-1.32

Efq

-1.27

 ―――――

-1.25

 ſtate

-1.20

$_"

-1.16

 utafitiHapana

-1.14

 houſe

-1.13

 purpoſe

-1.11

 faſt

-1.10

 Anſ

-1.10

POSITIVE LOGITS

↵↵

1.02

0.99

0.97

↵

0.93

0.91

<eos>

0.91

0.87

is

0.81

↵↵↵

0.76

Activations Density 0.194%

ellipsis and related punctuation indicating pauses or omissions in speech or writing

No Comments

No Known Activations