INDEX

Explanations

acronyms related to government agencies

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "DO" in relation to various government departments and policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Gaza

-0.79

Reviewer

-0.76

ulates

-0.70

ãĤ¼ãĤ¦ãĤ¹

-0.69

thur

-0.68

ulating

-0.68

 Scourge

-0.68

ICAN

-0.66

 Preferences

-0.65

taboola

-0.64

POSITIVE LOGITS

ppel

1.19

herty

1.14

omsday

1.12

ctr

1.02

zens

1.00

lyak

1.00

oms

0.99

berman

0.94

lez

0.89

omed

0.86

Activations Density 0.030%

acronyms related to government agencies

occurrences of the abbreviation "DO" in relation to various government departments and policies

No Comments

No Known Activations