INDEX

Explanations

technical terminology and concepts related to various fields such as science and engineering

oai_token-act-pair · gpt-3.5-turbo

phrases related to comparisons and categories

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Images

-0.78

Ys

-0.77

 fingerprints

-0.75

mails

-0.75

words

-0.75

IDs

-0.74

yrights

-0.72

 answers

-0.72

 needles

-0.71

ciating

-0.71

POSITIVE LOGITS

 semi

1.07

 multip

1.03

 intermediate

1.00

 Intermediate

1.00

 hybrid

0.99

 transitional

0.98

traditional

0.96

 Semi

0.96

classic

0.94

 multic

0.93

Activations Density 0.722%

technical terminology and concepts related to various fields such as science and engineering

phrases related to comparisons and categories

No Comments

No Known Activations