INDEX

Explanations

large amounts, often in the context of money or donations

oai_token-act-pair · gpt-3.5-turbo

mentions of amounts of money, particularly those that are $500

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

The number 500

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

swick

-0.78

wered

-0.78

ophon

-0.76

acia

-0.75

warts

-0.71

isman

-0.71

oglobin

-0.70

Osw

-0.70

udic

-0.69

atic

-0.69

POSITIVE LOGITS

0.80

 ILCS

0.79

px

0.79

charg

0.77

ESSION

0.76

+)

0.76

ertodd

0.76

MHz

0.73

+.

0.73

Activations Density 0.028%

large amounts, often in the context of money or donations

mentions of amounts of money, particularly those that are $500

The number 500

No Comments

No Known Activations