INDEX

Explanations

phrases related to declining to comment or provide information

oai_token-act-pair · gpt-3.5-turbo

instances of entities declining to provide comments or details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soDeliveryDate

-0.99

footed

-0.72

aldi

-0.70

abiding

-0.68

mill

-0.67

lies

-0.65

grain

-0.64

 Gone

-0.63

lined

-0.63

Cent

-0.63

POSITIVE LOGITS

 endorse

1.19

 disclose

1.06

 speculate

1.06

 participate

1.04

 criticize

1.02

 comment

1.01

 identify

1.00

 specify

1.00

 discuss

0.99

 characterize

0.99

Activations Density 0.052%

phrases related to declining to comment or provide information

instances of entities declining to provide comments or details

No Comments

No Known Activations