INDEX

Explanations

field-specific terms, abbreviations, and codes related to technology and information

oai_token-act-pair · gpt-3.5-turbo

terms and values related to measurements and statistics

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

Artist

-0.57

âĵĺ

-0.51

Hide

-0.50

icter

-0.50

Interstitial

-0.50

UCT

-0.49

 behav

-0.48

soDeliveryDate

-0.48

 Conserv

-0.48

 causation

-0.48

POSITIVE LOGITS

PsyNetMessage

0.67

ãĥ¯ãĥ³

0.60

pees

0.59

tarians

0.56

illion

0.54

iversary

0.54

ocre

0.53

 height

0.52

eno

0.51

tarian

0.51

Activations Density 0.983%

field-specific terms, abbreviations, and codes related to technology and information

terms and values related to measurements and statistics

No Comments

No Known Activations