INDEX

Explanations

the word "being."

oai_token-act-pair · gpt-3.5-turbo

the concept of "being" 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

PsyNetMessage

-0.83

inav

-0.72

 fray

-0.67

NetMessage

-0.66

 Times

-0.65

 Highlands

-0.63

 Explosion

-0.61

 Strait

-0.61

 Globe

-0.58

 Topics

-0.58

POSITIVE LOGITS

 able

1.45

 aware

1.00

 unable

1.00

 bitten

0.91

 judged

0.88

 thankful

0.88

 eaten

0.87

 immersed

0.86

 overwhelmed

0.86

held

0.84

Activations Density 0.067%

the word "being."

the concept of "being" in various contexts

No Comments

No Known Activations