INDEX

Explanations

phrases related to addition or increase

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate an increase or addition of context or information

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

neys

-0.66

ologue

-0.65

ocene

-0.65

 accessed

-0.64

ansas

-0.64

anners

-0.63

 exits

-0.62

ioned

-0.62

adian

-0.61

Cry

-0.60

POSITIVE LOGITS

 frustration

0.77

 suspense

0.74

 tension

0.74

balance

0.72

 realism

0.72

 mistrust

0.71

 tensions

0.70

 suspicions

0.70

 confusion

0.69

capacity

0.68

Activations Density 0.062%

phrases related to addition or increase

phrases that indicate an increase or addition of context or information

No Comments

No Known Activations