INDEX

Explanations

phrases related to reasoning or explanation

oai_token-act-pair · gpt-3.5-turbo

the word "why" or variations of it to indicate reasoning or justification

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

MM

-0.68

 tuber

-0.67

 phys

-0.62

 Ranger

-0.61

 polymorph

-0.61

 Winged

-0.60

 Suzuki

-0.60

 skelet

-0.58

 Juda

-0.58

 Roller

-0.58

POSITIVE LOGITS

why

1.02

soever

0.89

why

0.87

forward

0.82

WHY

0.79

ioned

0.77

ratulations

0.71

utterstock

0.68

iatus

0.68

ctuary

0.68

Activations Density 0.026%

phrases related to reasoning or explanation

the word "why" or variations of it to indicate reasoning or justification

No Comments

No Known Activations