INDEX

Explanations

phrases related to conflict and confrontation

oai_token-act-pair · gpt-3.5-turbo

repeated special characters or symbols, particularly the "Ŀ"

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 obser

-0.75

 incorpor

-0.71

 disadvant

-0.69

 ende

-0.68

 incent

-0.67

 Palestin

-0.66

 contrace

-0.65

 mathemat

-0.64

 unwanted

-0.63

 sacrific

-0.62

POSITIVE LOGITS

ï¸ı

0.95

Â¯

0.95

ï¸

0.81

ÃĽ

0.77

âĢł

0.76

ttp

0.74

Â°

0.74

âĻ

0.73

cue

0.72

tra

0.72

Activations Density 0.184%

phrases related to conflict and confrontation

repeated special characters or symbols, particularly the "Ŀ"

No Known Activations