INDEX

Explanations

negations and exceptions in statements

oai_token-act-pair · gpt-3.5-turbo

negative phrases or the word "not."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

PDATE

-0.78

 Pric

-0.76

GGGGGGGG

-0.72

 Cutter

-0.71

 snipp

-0.70

 Canaveral

-0.64

bats

-0.63

Said

-0.63

tons

-0.63

 Done

-0.62

POSITIVE LOGITS

 intend

1.23

 condone

1.23

 preclude

1.12

 necessarily

1.09

 require

1.05

 belong

1.05

 hesitate

1.04

 reside

1.04

 constitute

1.04

 exist

1.04

Activations Density 0.089%

negations and exceptions in statements

negative phrases or the word "not."

No Comments

No Known Activations