INDEX

Explanations

words related to negative actions or attitudes towards others

oai_token-act-pair · gpt-3.5-turbo

words related to "demand" or "call for action."

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

IFrame

Link

Negative Logits

WAYS

-0.80

 supper

-0.69

 Elves

-0.68

URN

-0.66

ORY

-0.66

Aid

-0.64

WAY

-0.64

OWS

-0.64

ORED

-0.64

 Hole

-0.63

POSITIVE LOGITS

agogue

1.11

onym

1.07

ographically

1.05

agog

1.04

igration

1.02

ploy

1.01

ilit

1.00

otions

0.99

utation

0.97

ixed

0.95

Activations Density 0.008%

words related to negative actions or attitudes towards others

words related to "demand" or "call for action."

No Known Activations