INDEX

Explanations

phrases indicating a certain level or degree of something

oai_token-act-pair · gpt-3.5-turbo

quantifiers and articles indicating amounts or qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RAW

-0.80

aris

-0.77

EDIT

-0.74

ULTS

-0.73

 sorts

-0.72

mins

-0.71

-0.70

ulously

-0.70

CTV

-0.70

aturday

-0.69

POSITIVE LOGITS

 deterrent

1.00

 nuisance

0.99

 tease

0.98

 coincidence

0.96

 stretch

0.92

 gamble

0.90

 hassle

0.88

 novelty

0.87

 burden

0.87

 mystery

0.87

Activations Density 0.080%

phrases indicating a certain level or degree of something

quantifiers and articles indicating amounts or qualities

No Comments

No Known Activations