INDEX

Explanations

phrases related to proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

references to risks and statistics related to health and nutrition

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

razil

-0.81

Hex

-0.80

Mew

-0.78

 Penny

-0.78

Zot

-0.77

 Paper

-0.77

 Tara

-0.75

 Wonders

-0.74

Peb

-0.74

 Kash

-0.73

POSITIVE LOGITS

channelAvailability

0.91

Sr

0.91

Anthony

0.86

Jr

0.84

sr

0.82

athi

0.81

 lightsaber

0.79

Season

0.79

ĩ

0.79

sr

0.79

Activations Density 0.328%

phrases related to proper nouns or names

references to risks and statistics related to health and nutrition

No Comments

No Known Activations