INDEX

Explanations

words ending in "-ing" that relate to actions or processes

oai_token-act-pair · gpt-3.5-turbo

gerunds and present participles in various contexts

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

ULTS

-0.65

Pwr

-0.60

TRY

-0.58

 Polk

-0.57

CHR

-0.55

 è£ıç

-0.54

 Galile

-0.53

Downloadha

-0.51

 supervised

-0.51

EXP

-0.50

POSITIVE LOGITS

ing

3.75

ed

1.93

ING

1.92

ingly

1.62

ings

1.58

ting

1.51

ning

1.46

ingham

1.45

bing

1.43

inging

1.41

Activations Density 0.063%

words ending in "-ing" that relate to actions or processes

gerunds and present participles in various contexts

No Comments

No Known Activations