INDEX

Explanations

phrases related to the potential consequences or outcomes of certain actions

oai_token-act-pair · gpt-3.5-turbo

modal verbs and phrases indicating potential actions or consequences

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Boot

-0.72

Pon

-0.65

 periodic

-0.63

 conferences

-0.61

 collaboration

-0.59

 Convention

-0.57

 contractual

-0.57

 consultation

-0.56

 Continuing

-0.56

 Helsinki

-0.56

POSITIVE LOGITS

 suffice

1.47

amas

0.81

ozy

0.79

arat

0.73

ŃĶ

0.72

onite

0.70

 disqual

0.70

 detract

0.67

 constitute

0.67

 qualify

0.67

Activations Density 0.354%

phrases related to the potential consequences or outcomes of certain actions

modal verbs and phrases indicating potential actions or consequences

No Comments

No Known Activations