INDEX

Explanations

phrases related to key points, concerns, or issues

oai_token-act-pair · gpt-3.5-turbo

statements or questions regarding existence or responsibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Nap

-0.71

Magn

-0.67

Vers

-0.66

agate

-0.66

roy

-0.60

ottenham

-0.59

 Powered

-0.58

 Admir

-0.58

 Hazard

-0.58

 Magn

-0.57

POSITIVE LOGITS

dar

0.70

yip

0.69

bet

0.68

illard

0.67

ategory

0.64

ONSORED

0.63

ĸļ

0.61

laun

0.61

>.

0.61

ibly

0.58

Activations Density 1.142%

phrases related to key points, concerns, or issues

statements or questions regarding existence or responsibility

No Comments

No Known Activations