INDEX

Explanations

technical articles or tutorials

oai_token-act-pair · gpt-3.5-turbo

references to articles or posts along with expressions of intention or planning related to those documents

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etheless

-0.71

artifacts

-0.67

['

-0.65

wcs

-0.64

 vanished

-0.63

aples

-0.63

ãĤ¨ãĥ«

-0.59

ËĪ

-0.58

ansas

-0.58

wings

-0.57

POSITIVE LOGITS

we

1.17

0.88

you

0.75

fter

0.69

We

0.68

 Doodle

0.66

we

0.65

Pru

0.65

 VICE

0.65

 Stefan

0.64

Activations Density 0.132%

technical articles or tutorials

references to articles or posts along with expressions of intention or planning related to those documents

No Comments

No Known Activations