INDEX

Explanations

phrases related to legal entities or processes

oai_token-act-pair · gpt-3.5-turbo

terms associated with legal entities and geographical locations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ibilities

-0.79

itude

-0.76

NEC

-0.74

itud

-0.72

orses

-0.67

ages

-0.66

cub

-0.66

 highs

-0.64

ably

-0.62

ibly

-0.62

POSITIVE LOGITS

osate

0.86

vertising

0.81

GROUP

0.72

Ware

0.71

 Countdown

0.64

cest

0.64

Lens

0.63

Ħ¢

0.63

 Dictionary

0.63

WAY

0.62

Activations Density 0.162%

phrases related to legal entities or processes

terms associated with legal entities and geographical locations

No Comments

No Known Activations