INDEX

Explanations

specific entities related to certain locations or organizations

oai_token-act-pair · gpt-3.5-turbo

words associated with governmental and organizational structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Interstitial

-0.78

 seiz

-0.78

é¾įå

-0.76

Ô

-0.72

ModLoader

-0.71

 sovere

-0.69

awaru

-0.68

uyomi

-0.68

FTWARE

-0.67

 illum

-0.66

POSITIVE LOGITS

rup

0.70

ibles

0.69

glers

0.69

lation

0.67

ibly

0.66

ounters

0.64

peak

0.62

ourcing

0.62

ctor

0.62

 Contra

0.61

Activations Density 0.597%

specific entities related to certain locations or organizations

words associated with governmental and organizational structures

No Comments

No Known Activations