INDEX

Explanations

mentions of the Federal Reserve

oai_token-act-pair · gpt-3.5-turbo

mentions of federal institutions or government entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Clever

-0.85

velt

-0.79

vier

-0.77

ppard

-0.74

ammers

-0.73

oldemort

-0.72

rained

-0.71

upon

-0.71

lihood

-0.70

{"

-0.69

POSITIVE LOGITS

 Reserve

1.08

 appellate

0.85

 Bureau

0.82

 Election

0.76

 Federal

0.75

igr

0.75

 Government

0.75

 Aviation

0.74

 agency

0.73

 Credit

0.73

Activations Density 0.007%

mentions of the Federal Reserve

mentions of federal institutions or government entities

No Comments

No Known Activations