INDEX

Explanations

action verbs related to software functions

oai_token-act-pair · gpt-3.5-turbo

modal verbs, particularly the word "can," in various contexts related to ability and options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

rant

-0.80

TED

-0.75

Moz

-0.72

cule

-0.71

 Closing

-0.71

 Irving

-0.70

 Rising

-0.65

 Herman

-0.65

raining

-0.64

 Lawrence

-0.64

POSITIVE LOGITS

't

1.19

 optionally

1.14

 customize

1.03

 manipulate

0.96

ister

0.96

adian

0.94

ISTER

0.94

NOT

0.93

 utilize

0.91

isters

0.91

Activations Density 0.179%

action verbs related to software functions

modal verbs, particularly the word "can," in various contexts related to ability and options

No Comments

No Known Activations