INDEX

Explanations

What is related to locations and organizations

oai_token-act-pair · gpt-3.5-turbo

references to groups of people or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Outside

-0.43

Redd

-0.41

amaz

-0.40

luster

-0.40

Exc

-0.39

Translation

-0.39

Moving

-0.39

Huh

-0.39

CCC

-0.39

Yo

-0.39

POSITIVE LOGITS

 testified

0.71

 survived

0.70

 lasted

0.69

 apologised

0.68

 lived

0.68

 oversaw

0.68

 appeared

0.68

 sailed

0.67

 wandered

0.67

 boasted

0.67

Activations Density 0.791%

What is related to locations and organizations

references to groups of people or entities

No Comments

No Known Activations