INDEX

Explanations

questions ending with a question mark

oai_token-act-pair · gpt-3.5-turbo

questions posed in the text

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

yak

-0.66

ishable

-0.66

 marsh

-0.66

 wilderness

-0.65

lock

-0.64

rio

-0.64

hob

-0.63

 worm

-0.63

 striped

-0.62

 space

-0.62

POSITIVE LOGITS

 Surely

1.08

 Nope

1.07

 Wouldn

1.01

 Certainly

0.97

 Answer

0.96

ï¿½ï¿½ï¿½ï¿½

0.96

 Perhaps

0.95

 Probably

0.93

 Presumably

0.93

 Sadly

0.91

Activations Density 0.113%

questions ending with a question mark

questions posed in the text

No Comments

No Known Activations