INDEX

Explanations

numbers and measurements related to movies and TV shows

oai_token-act-pair · gpt-3.5-turbo

phrases related to predictions about the success of films and series

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

 consultation

-0.74

 persuasion

-0.71

 observing

-0.71

cloth

-0.71

 consultations

-0.69

assian

-0.68

 calculations

-0.67

 coordination

-0.67

POL

-0.65

lifting

-0.65

POSITIVE LOGITS

 premiered

1.19

 feature

1.10

 contain

1.07

 showcase

1.07

 depict

1.06

 genre

1.04

 featured

1.04

 evoke

1.03

 audiences

1.03

 debuted

1.02

Activations Density 0.380%

numbers and measurements related to movies and TV shows

phrases related to predictions about the success of films and series

No Comments

No Known Activations