INDEX

Explanations

software engineering-related terms and phrases

oai_token-act-pair · gpt-3.5-turbo

terms related to various forms of events, services, and projects

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

 thereto

-0.74

 âĢ¦"

-0.72

 thereof

-0.71

opausal

-0.68

.","

-0.67

 otherwise

-0.66

Ïī

-0.64

 ..."

-0.63

Î¿

-0.62

POSITIVE LOGITS

 Facts

0.87

 Profile

0.86

resa

0.86

 Differences

0.84

 Description

0.84

 Categories

0.83

tymology

0.83

 Comparison

0.82

vertising

0.79

cyclopedia

0.78

Activations Density 0.344%

software engineering-related terms and phrases

terms related to various forms of events, services, and projects

No Comments

No Known Activations