INDEX

Explanations

dates and time-related words

oai_token-act-pair · gpt-3.5-turbo

phrases indicating time periods and counts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ulla

-0.63

 birthplace

-0.60

Lost

-0.57

ļéĨĴ

-0.57

 resides

-0.57

 deserving

-0.55

eal

-0.55

Reviewer

-0.53

 BEFORE

-0.51

 roots

-0.51

POSITIVE LOGITS

1.07

1.05

1.04

1.03

1.00

0.98

Activations Density 0.088%

dates and time-related words

phrases indicating time periods and counts

No Comments

No Known Activations