INDEX

Explanations

words or phrases related to logical reasoning and making sense

oai_token-act-pair · gpt-3.5-turbo

phrases indicating logical 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

enne

-0.77

psy

-0.72

aunting

-0.71

ritical

-0.70

quart

-0.70

astered

-0.68

leted

-0.67

inters

-0.67

otin

-0.66

tin

-0.65

POSITIVE LOGITS

INESS

0.75

why

0.73

WHY

0.71

ãħĭ

0.70

é¾įå¥ĳå£«

0.70

 behavi

0.70

 Eater

0.69

edIn

0.69

 partName

0.67

 Marketable

0.66

Activations Density 0.023%

words or phrases related to logical reasoning and making sense

phrases indicating logical reasoning or justification

No Comments

No Known Activations