INDEX

Explanations

phrases related to making changes or modifications

oai_token-act-pair · gpt-3.5-turbo

terms related to legal amendments or changes in regulations

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

cade

-0.74

jam

-0.65

ulhu

-0.64

ther

-0.61

way

-0.61

fare

-0.60

thing

-0.60

iPhone

-0.58

iac

-0.58

éļ

-0.58

POSITIVE LOGITS

ulate

0.90

imar

0.83

iate

0.83

 existing

0.82

orate

0.80

orously

0.77

ively

0.73

ibly

0.72

uate

0.71

ments

0.70

Activations Density 0.117%

phrases related to making changes or modifications

terms related to legal amendments or changes in regulations

No Comments

No Known Activations