INDEX

Explanations

queries or questions ending with a question mark

oai_token-act-pair · gpt-3.5-turbo

interrogative sentences or questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 encount

-0.81

eping

-0.71

cipled

-0.69

aled

-0.66

 blob

-0.66

aku

-0.65

 battered

-0.64

aler

-0.64

aper

-0.63

neau

-0.63

POSITIVE LOGITS

 Where

1.02

 Surely

1.02

.?

1.01

 Somebody

0.99

Why

0.98

 Certainly

0.97

 Anyway

0.94

 Probably

0.94

[*

0.94

 What

0.92

Activations Density 0.091%

queries or questions ending with a question mark

interrogative sentences or questions

No Comments

No Known Activations