INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

instances of empty or uninformative content

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

soever

-0.72

rum

-0.69

veh

-0.69

 Noon

-0.65

terness

-0.64

 Corm

-0.61

abus

-0.60

 entitle

-0.60

 allowances

-0.60

ares

-0.59

POSITIVE LOGITS

ebus

0.89

utsche

0.88

odcast

0.84

vernment

0.83

ctions

0.82

ffee

0.81

eers

0.81

xon

0.80

qua

0.80

ctive

0.79

Activations Density 0.052%

proper nouns or names

instances of empty or uninformative content

No Comments

No Known Activations