INDEX

Explanations

negative statements or sentiments

oai_token-act-pair · gpt-3.5-turbo

negations or expressions indicating the absence of something

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

rift

-0.75

Pierre

-0.64

æĥ

-0.62

 weap

-0.61

CRIP

-0.61

 Spectrum

-0.60

 Rouge

-0.59

 Pair

-0.58

éĥ

-0.57

athe

-0.57

POSITIVE LOGITS

yet

1.20

 been

1.14

yet

1.03

icably

1.01

hin

1.01

 gotten

1.01

epad

0.98

icable

0.97

been

0.92

 bothered

0.90

Activations Density 0.070%

negative statements or sentiments

negations or expressions indicating the absence of something

No Comments

No Known Activations