INDEX

Explanations

statements asserting facts or opinions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating market trends and business activities

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

 thereof

-1.01

↵Âł

-0.89

Firstly

-0.79

 ðŁĻĤ

-0.77

Ingredients

-0.76

[&

-0.74

Cause

-0.70

ãĥĺ

-0.70

Honestly

-0.70

Liter

-0.70

POSITIVE LOGITS

 lawmakers

0.83

 automakers

0.77

 Americans

0.77

 companies

0.75

 policymakers

0.74

 America

0.72

 Southwest

0.72

 Britain

0.71

 analysts

0.71

Activations Density 0.943%

statements asserting facts or opinions

phrases indicating market trends and business activities

No Comments

No Known Activations