INDEX

Explanations

phrases related to physical transformation or change

oai_token-act-pair · gpt-3.5-turbo

phrases describing transformations or formations of various substances or structures

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

Not in Any Lists

No Comments

Negative Logits

 editors

-0.91

 attendees

-0.84

votes

-0.83

 tweets

-0.81

 Elections

-0.79

 Sundays

-0.78

girls

-0.78

 administrators

-0.77

Events

-0.77

IDs

-0.76

POSITIVE LOGITS

 rectangle

1.12

 layer

1.09

 mixture

1.06

 thicker

1.06

 continuous

1.05

 thick

1.03

 dense

1.02

 visc

1.02

 rectangular

1.01

 spiral

1.01

Activations Density 0.348%

phrases related to physical transformation or change

phrases describing transformations or formations of various substances or structures

No Comments

No Known Activations