INDEX

Explanations

verbs indicating contemplation or consideration

oai_token-act-pair · gpt-3.5-turbo

phrases that initiate questions or address the reader's curiosity

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

nown

-0.71

©¶æ¥µ

-0.67

imar

-0.66

 realise

-0.64

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.64

pex

-0.64

qua

-0.62

udeb

-0.62

%.

-0.62

tu

-0.61

POSITIVE LOGITS

 warr

0.66

 anything

0.64

 dessert

0.63

 exclus

0.62

 inspiration

0.62

 yourself

0.62

 finer

0.60

 throne

0.60

 athlet

0.60

 caffeine

0.58

Activations Density 0.359%

verbs indicating contemplation or consideration

phrases that initiate questions or address the reader's curiosity

No Comments

No Known Activations