INDEX

Explanations

words related to exception or differentiation

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate exceptions or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ANS

-0.89

dayName

-0.77

avan

-0.74

nown

-0.70

ahead

-0.70

accompan

-0.69

arna

-0.69

ans

-0.67

DOWN

-0.65

rait

-0.64

POSITIVE LOGITS

 occasional

0.87

 occasionally

0.79

 sporadic

0.72

 superficial

0.72

 those

0.71

 briefly

0.69

 anecdotal

0.69

 anecd

0.69

 mater

0.68

 spor

0.66

Activations Density 0.048%

words related to exception or differentiation

phrases that indicate exceptions or conditions

No Comments

No Known Activations