INDEX

Explanations

punctuation marks, particularly colons

oai_token-act-pair · gpt-3.5-turbo

icons or emoticons used to express emotions or reactions

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

ifying

-0.79

utive

-0.74

izabeth

-0.71

idad

-0.70

 conversions

-0.69

ified

-0.67

heed

-0.67

ilingual

-0.65

ilitation

-0.64

ibles

-0.64

POSITIVE LOGITS

::::::::

1.68

::::

1.41

;;;;;;;;;;;;

0.87

;;;;;;;;

0.87

-(

0.86

,,,,

0.85

,,,,,,,,

0.83

cause

0.70

hover

0.68

;;;;

0.68

Activations Density 0.032%

punctuation marks, particularly colons

icons or emoticons used to express emotions or reactions

No Comments

No Known Activations