INDEX

Explanations

the word "don't" followed by a negative verb contraction

oai_token-act-pair · gpt-3.5-turbo

negations or phrases expressing dissent

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Reloaded

-0.76

Reviewer

-0.76

soType

-0.74

çĦ

-0.72

estern

-0.71

 Penguin

-0.69

itiz

-0.69

pter

-0.66

 behavi

-0.64

foundland

-0.64

POSITIVE LOGITS

 necessarily

1.08

 bother

1.00

 anymore

0.91

ude

0.84

cha

0.81

 hesitate

0.81

 seem

0.81

 expect

0.81

 know

0.80

rave

0.80

Activations Density 0.100%

the word "don't" followed by a negative verb contraction

negations or phrases expressing dissent

No Known Activations