INDEX

Explanations

word sequences related to evidence and support

oai_token-act-pair · gpt-3.5-turbo

phrases related to evidence and support in various contexts

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

ppa

-0.82

chn

-0.81

adobe

-0.80

arted

-0.77

NCT

-0.71

DragonMagazine

-0.71

forum

-0.70

ahime

-0.70

umb

-0.68

 ILCS

-0.68

POSITIVE LOGITS

 assertions

1.06

 causation

1.04

 hypotheses

1.00

 validity

0.98

 tampering

0.93

independence

0.92

 claims

0.91

 assertion

0.90

 innocence

0.88

why

0.85

Activations Density 0.125%

word sequences related to evidence and support

phrases related to evidence and support in various contexts

No Comments

No Known Activations