INDEX

Explanations

phrases indicating uncertainty or indecision

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "what."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

robe

-0.67

cean

-0.63

eer

-0.60

âĵĺ

-0.60

uttering

-0.59

ster

-0.59

ãĥ¼ãĥ³

-0.59

por

-0.59

fish

-0.58

trop

-0.58

POSITIVE LOGITS

soever

1.14

 happens

1.01

 happened

0.97

 sorts

0.91

 kinds

0.89

 happ

0.86

 exactly

0.80

 transpired

0.79

nces

0.75

 else

0.73

Activations Density 0.116%

phrases indicating uncertainty or indecision

occurrences of the word "what."

No Comments

No Known Activations