INDEX

Explanations

acronyms and abbreviations of organizations or institutions

oai_token-act-pair · gpt-3.5-turbo

acronyms or abbreviations relating to organizations or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

taboola

-0.66

 ç¥ŀ

-0.65

isine

-0.64

lore

-0.64

 trave

-0.63

speed

-0.62

*=-

-0.61

perty

-0.60

things

-0.60

dab

-0.59

POSITIVE LOGITS

 logo

0.89

 process

0.85

 Directorate

0.82

 directive

0.79

 database

0.79

 Framework

0.78

 hierarchy

0.78

 Newsletter

0.76

 program

0.76

 consortium

0.74

Activations Density 0.208%

acronyms and abbreviations of organizations or institutions

acronyms or abbreviations relating to organizations or groups

No Comments

No Known Activations