INDEX

Explanations

references to sharp objects, particularly knives

oai_token-act-pair · gpt-3.5-turbo

references to knives in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

mberg

-0.89

ICLE

-0.78

rian

-0.77

leep

-0.76

tainment

-0.76

 Gutenberg

-0.75

ysical

-0.74

rians

-0.73

rix

-0.71

alse

-0.71

POSITIVE LOGITS

 blades

1.02

 blade

1.01

 knife

0.98

 knives

0.98

 scissors

0.97

knife

0.93

 slicing

0.89

 cutter

0.88

 wielding

0.85

powder

0.84

Activations Density 0.026%

references to sharp objects, particularly knives

references to knives in various contexts

No Comments

No Known Activations