INDEX

Explanations

numerical values with associated symbols or units

oai_token-act-pair · gpt-3.5-turbo

numeric data and percentages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

rul

-0.71

 destro

-0.70

 undermin

-0.63

nesday

-0.62

 manif

-0.60

wagen

-0.60

 disadvant

-0.59

 predec

-0.55

 horizont

-0.55

ividual

-0.54

POSITIVE LOGITS

 ãĥ

0.50

 RELEASE

0.48

 ILCS

0.47

ARM

0.46

 âĢº

0.45

<<

0.45

 Registered

0.44

IPM

0.43

 Region

0.42

Activations Density 0.715%

numerical values with associated symbols or units

numeric data and percentages

No Comments

No Known Activations