INDEX

Explanations

adjectives used to describe characteristics or qualities

oai_token-act-pair · gpt-3.5-turbo

adjectives and descriptors related to characteristics and states

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

earchers

-0.68

proven

-0.63

ittees

-0.61

 Heard

-0.59

reon

-0.58

adr

-0.58

çīĪ

-0.58

Lost

-0.58

hig

-0.57

wan

-0.56

POSITIVE LOGITS

ness

1.63

NESS

1.28

nesses

1.25

ity

1.19

ly

1.01

liness

0.96

ities

0.92

 ones

0.89

est

0.84

 versus

0.82

Activations Density 0.235%

adjectives used to describe characteristics or qualities

adjectives and descriptors related to characteristics and states

No Comments

No Known Activations