INDEX

Explanations

phrases related to obtaining information or evidence

oai_token-act-pair · gpt-3.5-turbo

phrases related to acquiring or gaining access to information or resources

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

heartedly

-0.77

erness

-0.64

psc

-0.64

hov

-0.64

gaard

-0.59

cas

-0.58

mans

-0.58

brace

-0.57

 Mouth

-0.57

timer

-0.56

POSITIVE LOGITS

 permission

0.86

å¥³

0.79

andom

0.77

 authorization

0.76

DragonMagazine

0.73

 access

0.73

 signatures

0.70

 warrants

0.70

OGR

0.70

 permits

0.70

Activations Density 0.040%

phrases related to obtaining information or evidence

phrases related to acquiring or gaining access to information or resources

No Comments

No Known Activations