INDEX

Explanations

words related to artificial intelligence (AI)

oai_token-act-pair · gpt-3.5-turbo

mentions of artificial intelligence (AI) and its applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

atche

-0.83

ados

-0.77

ings

-0.77

ifest

-0.74

lain

-0.72

 Townsend

-0.70

stable

-0.70

Jer

-0.68

eous

-0.66

scenes

-0.66

POSITIVE LOGITS

AI

0.98

AI

0.94

 Doodle

0.72

 nomine

0.71

 hoard

0.71

 theoret

0.70

onomous

0.69

 hemor

0.67

 flaw

0.67

 sophistication

0.67

Activations Density 0.009%

words related to artificial intelligence (AI)

mentions of artificial intelligence (AI) and its applications

No Comments

No Known Activations