INDEX

Explanations

instances of the word "feedback" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Dyer

-0.82

 battre

-0.73

ro

-0.68

 Byers

-0.66

st

-0.61

istra

-0.60

Mu

-0.60

men

-0.59

 πό

-0.59

Ma

-0.59

POSITIVE LOGITS

 feedback

2.24

feedback

2.00

 Feedback

1.97

Feedback

1.87

 feedbacks

1.85

 FEEDBACK

1.70

edback

1.66

FEEDBACK

1.49

反馈

1.29

 pleaſure

1.13

Activations Density 0.095%

instances of the word "feedback" and its variations in various contexts

No Comments

No Known Activations