INDEX

Explanations

phrases related to taking action or making decisions

oai_token-act-pair · gpt-3.5-turbo

imperative phrases urging action

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

holm

-0.70

Cong

-0.70

eers

-0.68

 advertised

-0.65

 david

-0.65

 Smile

-0.63

 agre

-0.62

gian

-0.62

ler

-0.62

 Kamp

-0.61

POSITIVE LOGITS

 advantage

1.11

aways

1.10

 heed

0.97

overs

0.90

 care

0.90

 aback

0.88

OVER

0.80

autions

0.80

 precedence

0.78

 precautions

0.77

Activations Density 0.122%

phrases related to taking action or making decisions

imperative phrases urging action

No Comments

No Known Activations