INDEX

Explanations

keywords and phrases related to rankings or lists

oai_token-act-pair · gpt-3.5-turbo

the word "Top" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Lauder

-0.65

 Gaul

-0.64

ufact

-0.63

 Advent

-0.62

otive

-0.61

 Baldwin

-0.60

ATIONAL

-0.59

 Arri

-0.58

 Griffith

-0.58

ibo

-0.58

POSITIVE LOGITS

ographical

1.17

most

1.11

ography

1.06

ology

0.99

deck

0.98

ographic

0.95

ographically

0.95

eka

0.91

ologically

0.91

ographies

0.85

Activations Density 0.039%

keywords and phrases related to rankings or lists

the word "Top" in various contexts

No Comments

No Known Activations