INDEX

Explanations

phrases related to research, analysis, and decision-making processes

oai_token-act-pair · gpt-3.5-turbo

detectable patterns related to data processing, analysis, and responses 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 @ 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

Boy

-0.48

OV

-0.47

BUG

-0.47

ASED

-0.47

OOOOOOOO

-0.47

guyen

-0.46

 Libertarian

-0.46

Ott

-0.46

VID

-0.46

OWN

-0.44

POSITIVE LOGITS

hips

1.18

paces

1.10

hip

1.09

pace

1.03

mith

0.99

hops

0.99

pring

0.98

ynthesis

0.92

ystem

0.87

heet

0.85

Activations Density 0.845%

phrases related to research, analysis, and decision-making processes

detectable patterns related to data processing, analysis, and responses in various contexts

No Comments

No Known Activations