INDEX

Explanations

words related to being filled with something

oai_token-act-pair · gpt-3.5-turbo

words associated with being filled or packed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Minor

-0.65

 moot

-0.61

 precedent

-0.61

Car

-0.60

 decentral

-0.60

 minimum

-0.60

Das

-0.59

 Mechan

-0.59

 turnover

-0.59

TA

-0.59

POSITIVE LOGITS

filled

4.00

packed

2.01

laden

1.81

fill

1.77

ridden

1.63

lined

1.50

loaded

1.40

covered

1.38

stained

1.34

 filled

1.11

Activations Density 0.023%

words related to being filled with something

words associated with being filled or packed

No Comments

No Known Activations