INDEX

Explanations

prepositions used to indicate relationships between elements in a sentence

oai_token-act-pair · gpt-3.5-turbo

references to methods or approaches taken 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nces

-0.65

oor

-0.64

cellent

-0.63

oglu

-0.63

arest

-0.62

 Traps

-0.62

 Achievements

-0.62

azeera

-0.61

zens

-0.59

aters

-0.59

POSITIVE LOGITS

 behalf

0.90

 regards

0.80

 selecting

0.74

 deciding

0.72

ModLoader

0.71

 figuring

0.70

 regard

0.68

 choosing

0.67

 resolving

0.67

 subdu

0.67

Activations Density 0.585%

prepositions used to indicate relationships between elements in a sentence

references to methods or approaches taken in various contexts

No Comments

No Known Activations