INDEX

Explanations

the word "lied" in various contexts

oai_token-act-pair · gpt-3.5-turbo

past participles of verbs

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

arta

-0.85

DNA

-0.74

OUNT

-0.71

Introduced

-0.71

illin

-0.70

asio

-0.69

Det

-0.68

Slot

-0.67

forums

-0.66

Solution

-0.66

POSITIVE LOGITS

ied

0.73

onic

0.72

ezvous

0.70

onymous

0.66

imentary

0.66

IED

0.65

ividual

0.63

Io

0.63

gments

0.62

ying

0.60

Activations Density 0.014%

the word "lied" in various contexts

past participles of verbs

No Comments

No Known Activations