INDEX

Explanations

technical terms, possibly related to information technology

oai_token-act-pair · gpt-3.5-turbo

words related to origin and classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Sunshine

-0.54

 Hyde

-0.53

 Settlement

-0.52

 Sutherland

-0.52

 distraction

-0.50

 Hurt

-0.48

 Semin

-0.48

 Trojan

-0.47

 Violence

-0.47

 Franks

-0.46

POSITIVE LOGITS

ishly

0.92

ifully

0.92

arily

0.92

ially

0.86

cially

0.81

pecially

0.80

atively

0.80

atically

0.80

ically

0.80

wise

0.80

Activations Density 0.733%

technical terms, possibly related to information technology

words related to origin and classification

No Comments

No Known Activations