INDEX

Explanations

indications of statistical probabilities

oai_token-act-pair · gpt-3.5-turbo

suffixes or word endings that indicate categories or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

capt

-0.70

Interstitial

-0.69

>[

-0.66

TIT

-0.65

PLIED

-0.63

essage

-0.63

 keynote

-0.62

ibrary

-0.62

por

-0.62

ãģ¾

-0.62

POSITIVE LOGITS

osate

1.01

onom

0.76

vere

0.69

 Cycle

0.67

irection

0.65

yp

0.65

ually

0.65

rate

0.64

 Maps

0.62

 Archdemon

0.62

Activations Density 0.101%

indications of statistical probabilities

suffixes or word endings that indicate categories or classifications

No Comments

No Known Activations