INDEX

Explanations

specific phrases containing the term "hard-working"

oai_token-act-pair · gpt-3.5-turbo

phrases related to hard work or dedication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ulhu

-1.05

çīĪ

-0.77

DragonMagazine

-0.76

 Rica

-0.73

ADRA

-0.73

 Noir

-0.71

ICAN

-0.71

 guiActiveUn

-0.71

éŃĶ

-0.70

 Creator

-0.70

POSITIVE LOGITS

sounding

1.30

eyed

1.22

looking

1.18

sized

1.15

minded

1.14

hearted

1.12

issue

1.09

legged

1.06

shaped

1.05

numbered

1.05

Activations Density 0.128%

specific phrases containing the term "hard-working"

phrases related to hard work or dedication

No Comments

No Known Activations