INDEX

Explanations

expressions of regret or acknowledgment of previous mistakes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Reſ

-1.28

 Anſ

-1.28

 Houſe

-1.20

 itſelf

-1.19

 ―――――

-1.18

 faſt

-1.18

 houſe

-1.17

 Theſe

-1.17

 pleaſure

-1.16

Efq

-1.11

POSITIVE LOGITS

 noted

1.15

 notes

1.13

 notable

1.09

 Note

1.01

 note

1.00

 Notable

0.97

 Notes

0.91

Note

0.89

Notable

0.85

note

0.79

Activations Density 0.143%

expressions of regret or acknowledgment of previous mistakes

No Comments

No Known Activations