INDEX

Explanations

words related to degree or intensity

oai_token-act-pair · gpt-3.5-turbo

adjectives that describe varying levels of restriction or severity in 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FORE

-0.70

owell

-0.68

cellent

-0.66

WAR

-0.65

isha

-0.65

vez

-0.64

 multiplied

-0.61

except

-0.61

vind

-0.61

MED

-0.60

POSITIVE LOGITS

 versions

1.35

 version

1.19

 ones

1.16

 than

1.11

 alternatives

1.08

 counterparts

1.07

 forms

1.05

 variants

1.02

 aspects

0.98

 sounding

0.96

Activations Density 0.238%

words related to degree or intensity

adjectives that describe varying levels of restriction or severity in contexts

No Comments

No Known Activations