INDEX

Explanations

terms related to specific product models and brands

oai_token-act-pair · gpt-3.5-turbo

specific references to events, products, or items of interest 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 @ 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

 undermin

-0.64

 disg

-0.64

 destro

-0.63

sic

-0.58

 conflic

-0.58

 corrid

-0.57

maximum

-0.56

 tiss

-0.55

 answ

-0.54

 comprom

-0.53

POSITIVE LOGITS

 Collection

0.72

 Profile

0.65

 Region

0.65

 Reviews

0.64

 Release

0.63

 Series

0.62

 Edition

0.62

 Abilities

0.61

 Forums

0.60

 âĵĺ

0.60

Activations Density 0.699%

terms related to specific product models and brands

specific references to events, products, or items of interest in various contexts

No Comments

No Known Activations