INDEX

Explanations

phrases related to various interests, potentially of political and community nature

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "interests" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aan

-0.80

ework

-0.72

BuyableInstoreAndOnline

-0.70

KING

-0.70

wolves

-0.67

ergy

-0.67

UNCH

-0.67

aston

-0.67

otte

-0.66

åī

-0.64

POSITIVE LOGITS

 interests

1.08

reprene

0.87

 territ

0.82

awaru

0.78

 Groups

0.74

igent

0.73

ĺħ

0.72

afe

0.72

 agric

0.72

 shareholders

0.70

Activations Density 0.040%

phrases related to various interests, potentially of political and community nature

references to the concept of "interests" in various contexts

No Comments

No Known Activations