INDEX

Explanations

word pairs with repetition for emphasis or accuracy

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

orthy

-0.90

uga

-0.84

atis

-0.80

 Authors

-0.78

Stage

-0.76

dor

-0.75

onso

-0.74

icans

-0.74

erves

-0.71

esta

-0.70

POSITIVE LOGITS

 ratio

1.11

 comparisons

1.06

 conversion

1.04

 ratios

1.00

 correspondence

1.00

 conversions

0.98

 converter

0.91

 transmission

0.89

 approach

0.88

 comparison

0.88

Activations Density 0.145%

word pairs with repetition for emphasis or accuracy

No Comments

No Known Activations