INDEX

Explanations

specific references to directions or positions within a physical object

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize the presence or quantity of a specific object or component

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Scotland

-0.65

abetes

-0.65

America

-0.64

Brexit

-0.64

WASHINGTON

-0.60

Turkey

-0.59

Russia

-0.59

Putin

-0.58

thood

-0.58

 among

-0.58

POSITIVE LOGITS

 aforementioned

1.12

 entire

1.12

 remainder

1.10

 latter

1.10

 slightest

1.06

ses

1.04

 entirety

1.00

 same

0.99

 rest

0.98

 whole

0.97

Activations Density 1.208%

specific references to directions or positions within a physical object

phrases that emphasize the presence or quantity of a specific object or component

No Comments

No Known Activations