INDEX

Explanations

specific words related to identification, certification, and magnificence

oai_token-act-pair · gpt-3.5-turbo

words related to scientific concepts or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

JP

-0.73

PRES

-0.68

iewicz

-0.67

CTV

-0.65

VK

-0.63

JM

-0.62

QUEST

-0.61

flies

-0.61

dimension

-0.61

 largeDownload

-0.60

POSITIVE LOGITS

atory

1.18

ific

1.13

ulty

0.99

ature

0.95

entials

0.94

ance

0.91

ates

0.90

ator

0.89

ators

0.89

acion

0.89

Activations Density 0.020%

specific words related to identification, certification, and magnificence

words related to scientific concepts or classifications

No Comments

No Known Activations