INDEX

Explanations

words related to ears or hearing

oai_token-act-pair · gpt-3.5-turbo

words that convey a sense of caution or warning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Strauss

-0.68

apo

-0.68

raviolet

-0.64

 Tsuk

-0.64

drm

-0.64

naires

-0.63

 pand

-0.62

arella

-0.61

 Ambro

-0.59

ktop

-0.59

POSITIVE LOGITS

nings

1.21

ning

1.03

lier

1.01

gments

0.90

wig

0.88

paio

0.85

owship

0.82

ls

0.81

ctic

0.81

cies

0.80

Activations Density 0.029%

words related to ears or hearing

words that convey a sense of caution or warning

No Comments

No Known Activations