INDEX

Explanations

sentences containing contrasting statements or opinions

oai_token-act-pair · gpt-3.5-turbo

instances of punctuation and their frequency of usage

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

¬¼

-0.60

UF

-0.46

ãĥ¥

-0.45

ivery

-0.44

etary

-0.43

ļéĨĴ

-0.43

herent

-0.43

Į

-0.42

reth

-0.42

§

-0.42

POSITIVE LOGITS

 however

0.81

 albeit

0.75

huh

0.73

 though

0.70

 please

0.68

 alas

0.66

 namely

0.66

 although

0.66

 meanwhile

0.63

etc

0.62

Activations Density 1.084%

sentences containing contrasting statements or opinions

instances of punctuation and their frequency of usage

No Comments

No Known Activations