INDEX

Explanations

phrases starting with "By," indicating a cause and effect relationship

oai_token-act-pair · gpt-3.5-turbo

the phrase "By" used to introduce explanations or observations

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

SPONSORED

-0.77

isable

-0.77

atem

-0.73

hyde

-0.72

SpaceEngineers

-0.66

idad

-0.65

MpServer

-0.62

 pains

-0.61

Ø§ÙĦ

-0.61

itives

-0.61

POSITIVE LOGITS

 virtue

1.06

 contrast

1.05

akuya

1.01

catch

0.95

 implication

0.83

stand

0.82

pass

0.79

products

0.74

 analogy

0.74

 sheer

0.74

Activations Density 0.041%

phrases starting with "By," indicating a cause and effect relationship

the phrase "By" used to introduce explanations or observations

No Comments

No Known Activations