INDEX

Explanations

phrases indicating a comparison of rates or growth between different time periods or generations

oai_token-act-pair · gpt-3.5-turbo

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

Negative Logits

 constitutionally

-0.81

 traitor

-0.81

 ransom

-0.74

 incompetent

-0.74

 inept

-0.72

 slightest

-0.72

 capit

-0.70

 expired

-0.70

 bellig

-0.70

 swearing

-0.69

POSITIVE LOGITS

Adds

1.12

Explore

1.06

Eventually

0.93

Researchers

0.92

Students

0.92

Growing

0.90

paces

0.88

Understanding

0.87

Interview

0.86

Working

0.85

Activations Density 0.543%

phrases indicating a comparison of rates or growth between different time periods or generations

No Known Activations