INDEX

Explanations

locations or place names

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to people and organizations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etheless

-0.80

BILITIES

-0.75

acters

-0.68

matically

-0.64

TABLE

-0.64

âĶĢâĶĢ

-0.62

 endorsements

-0.62

FORE

-0.61

FORMATION

-0.61

BILITY

-0.59

POSITIVE LOGITS

orius

1.09

inia

1.02

ington

1.01

ingham

0.99

alon

0.98

kel

0.98

ilon

0.97

enza

0.96

inski

0.93

rito

0.92

Activations Density 0.135%

locations or place names

proper nouns related to people and organizations

No Comments

No Known Activations