INDEX

Explanations

phrases introducing examples or clarifications

oai_token-act-pair · gpt-3.5-turbo

instances of the word "say" indicating reported speech or quotation

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

xtap

-0.78

leeve

-0.78

aughs

-0.72

OGR

-0.71

taboola

-0.66

wald

-0.65

obal

-0.65

folios

-0.65

 Compensation

-0.64

onut

-0.64

POSITIVE LOGITS

lihood

0.85

ings

0.83

 goodbye

0.80

 hello

0.73

ership

0.71

parts

0.67

lly

0.65

ies

0.64

volent

0.64

abouts

0.62

Activations Density 0.026%

phrases introducing examples or clarifications

instances of the word "say" indicating reported speech or quotation

No Comments

No Known Activations