INDEX

Explanations

instances where some action or event is linked to a specific entity or authority

oai_token-act-pair · gpt-3.5-turbo

references to ongoing situations or developments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Located

-0.69

ickets

-0.67

 Cipher

-0.67

thood

-0.65

Bee

-0.65

adoes

-0.64

Tools

-0.64

tein

-0.63

Storage

-0.61

Ability

-0.61

POSITIVE LOGITS

obin

0.86

EVA

0.78

 Canaver

0.75

furt

0.73

 Fowler

0.70

WARD

0.69

 TRUMP

0.68

nyder

0.68

 Rowling

0.67

arde

0.67

Activations Density 0.119%

instances where some action or event is linked to a specific entity or authority

references to ongoing situations or developments

No Comments

No Known Activations