INDEX

Explanations

hyphenated words

oai_token-act-pair · gpt-3.5-turbo

negative sentiments or criticisms

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 nursing

-0.85

 slog

-0.84

 climbing

-0.79

 swearing

-0.77

 icing

-0.76

 catast

-0.76

 aggravated

-0.76

 hydra

-0.76

 malf

-0.75

 popul

-0.75

POSITIVE LOGITS

Own

1.31

Country

1.29

Games

1.25

Aid

1.24

Ey

1.22

Tech

1.22

School

1.21

Specific

1.21

Strike

1.20

Imp

1.20

Activations Density 0.109%

hyphenated words

negative sentiments or criticisms

No Known Activations