INDEX

Explanations

time-related expressions, specifically focusing on past periods

oai_token-act-pair · gpt-3.5-turbo

phrases indicating duration or time spent on an activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ciplinary

-0.67

.[

-0.62

Champ

-0.62

Level

-0.61

cale

-0.60

oma

-0.60

ONSORED

-0.60

pin

-0.58

!.

-0.58

SPONSORED

-0.57

POSITIVE LOGITS

 entirety

1.55

 entire

1.37

 remainder

1.34

 majority

1.24

 bulk

1.10

 whole

1.10

 latter

1.06

 toughest

1.06

 longest

1.02

 brunt

1.01

Activations Density 0.174%

time-related expressions, specifically focusing on past periods

phrases indicating duration or time spent on an activity

No Comments

No Known Activations