INDEX

Explanations

words related to technology and projects or initiatives with specific names

oai_token-act-pair · gpt-3.5-turbo

mentions of control systems and specific projects or technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

aples

-0.72

azeera

-0.70

 inclined

-0.69

 flee

-0.68

 institution

-0.68

tyr

-0.68

 slump

-0.67

 notor

-0.65

 pronounce

-0.65

 collide

-0.64

POSITIVE LOGITS

*.

0.99

_.

0.91

0.81

 Reloaded

0.80

!.

0.78

 Revis

0.76

+.

0.76

 Syndrome

0.75

*,

0.74

Provider

0.74

Activations Density 0.357%

words related to technology and projects or initiatives with specific names

mentions of control systems and specific projects or technologies

No Comments

No Known Activations