INDEX

Explanations

phrases related to rules and guidelines

oai_token-act-pair · gpt-3.5-turbo

structured rules and guidelines 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 @ 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

idays

-0.74

caster

-0.71

 ILCS

-0.71

alan

-0.70

auga

-0.70

adas

-0.68

burgh

-0.68

:]

-0.64

ments

-0.63

asks

-0.62

POSITIVE LOGITS

 thumb

1.00

 physics

0.91

 therm

0.90

 propri

0.81

 precedence

0.80

 logic

0.74

 thirds

0.74

 gravity

0.74

 averages

0.73

 conduct

0.72

Activations Density 0.097%

phrases related to rules and guidelines

structured rules and guidelines in various contexts

No Comments

No Known Activations