INDEX

Explanations

phrases indicating a connection between a topic and some form of interaction or effect

oai_token-act-pair · gpt-3.5-turbo

prepositions and their usage in sentence constructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.72

........

-0.70

Ú

-0.69

 arrang

-0.68

 rather

-0.68

MAP

-0.67

\\\\\\\\

-0.66

PLA

-0.65

mone

-0.63

ahime

-0.62

POSITIVE LOGITS

 aren

0.74

 were

0.72

were

0.70

are

0.69

 weren

0.69

older

0.69

 differ

0.68

 differed

0.68

 Previous

0.61

ongyang

0.60

Activations Density 0.381%

phrases indicating a connection between a topic and some form of interaction or effect

prepositions and their usage in sentence constructions

No Comments

No Known Activations