INDEX

Explanations

instances where the word "could" is used in the context of suggesting possibilities or actions one can take

oai_token-act-pair · gpt-3.5-turbo

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

Maker

-0.67

holder

-0.64

core

-0.63

waters

-0.62

making

-0.60

AME

-0.60

 Yards

-0.59

oric

-0.58

members

-0.58

akes

-0.58

POSITIVE LOGITS

 feas

1.06

 conce

1.01

 theoretically

0.96

 hypot

0.95

 foresee

0.86

ivably

0.84

 tremend

0.81

 argue

0.81

've

0.80

 possibly

0.78

Activations Density 0.082%

instances where the word "could" is used in the context of suggesting possibilities or actions one can take

No Comments

No Known Activations