INDEX

Explanations

phrases related to efficiency and optimization

oai_token-act-pair · gpt-3.5-turbo

references to efficiency in various contexts

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

enegger

-0.83

warts

-0.79

wart

-0.72

jong

-0.71

acular

-0.70

den

-0.66

Dream

-0.66

planes

-0.66

FACE

-0.66

hair

-0.65

POSITIVE LOGITS

 efficiency

1.04

 efficient

1.00

 allocation

0.95

 inefficient

0.90

iencies

0.88

 tract

0.85

 utilization

0.83

idious

0.81

 alloc

0.80

 cooker

0.77

Activations Density 0.026%

phrases related to efficiency and optimization

references to efficiency in various contexts

No Comments

No Known Activations