INDEX

Explanations

terms related to technology and manufacturing

oai_token-act-pair · gpt-3.5-turbo

common nouns that represent various objects, concepts, or themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Returns

-0.74

 Kills

-0.68

laughs

-0.66

tains

-0.65

Attempts

-0.62

needs

-0.59

Has

-0.59

ALLY

-0.58

ãĤ¦ãĤ¹

-0.58

 Fixes

-0.58

POSITIVE LOGITS

 aren

1.33

are

1.29

 weren

1.27

 themselves

1.15

 were

1.15

 seem

1.08

 vary

1.06

 differ

1.02

 comprise

0.98

 appear

0.98

Activations Density 0.345%

terms related to technology and manufacturing

common nouns that represent various objects, concepts, or themes

No Comments

No Known Activations