INDEX

Explanations

phrases related to actively working on a task or project

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "working on."

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

Bey

-0.81

Champ

-0.72

few

-0.70

RL

-0.70

Override

-0.69

flies

-0.65

Jose

-0.65

ME

-0.64

YP

-0.64

Chel

-0.63

POSITIVE LOGITS

 behalf

1.56

eday

0.99

 occasion

0.82

 improving

0.79

 developing

0.78

sets

0.75

 impulse

0.74

ABE

0.74

 Saturdays

0.74

 preserving

0.73

Activations Density 0.089%

phrases related to actively working on a task or project

instances of the phrase "working on."

No Comments

No Known Activations