INDEX

Explanations

personal pronouns followed by verbs

oai_token-act-pair · gpt-3.5-turbo

references to people's actions and feelings towards others

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

Cla

-0.71

 Dunk

-0.64

 Burst

-0.61

 Beast

-0.61

 Bott

-0.60

 Vent

-0.60

 Marine

-0.58

 Radiation

-0.58

 Explosion

-0.58

 Sloan

-0.57

POSITIVE LOGITS

 deem

1.16

 deems

1.15

 dislike

1.15

 hadn

1.14

 shouldn

1.10

 couldn

1.05

 disliked

1.04

 disapprove

1.01

 cannot

0.99

 otherwise

0.99

Activations Density 0.148%

personal pronouns followed by verbs

references to people's actions and feelings towards others

No Comments

No Known Activations