INDEX

Explanations

mentions of applying skills, knowledge, rules, or standards in various contexts

oai_token-act-pair · gpt-3.5-turbo

phrases related to the application of skills, insights, and laws

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

etsk

-0.89

warts

-0.76

olulu

-0.68

aucuses

-0.67

 bedrooms

-0.67

ottesville

-0.62

akes

-0.62

çİĭ

-0.62

-0.61

ake

-0.60

POSITIVE LOGITS

 downwards

0.76

 liber

0.75

pmwiki

0.75

 corrective

0.75

 restraints

0.71

 downward

0.71

 harshly

0.70

 logic

0.70

 therape

0.69

 Gravity

0.68

Activations Density 0.101%

mentions of applying skills, knowledge, rules, or standards in various contexts

phrases related to the application of skills, insights, and laws

No Comments

No Known Activations