INDEX

Explanations

phrases related to physical location and architecture, particularly with a focus on features like floors and levels

oai_token-act-pair · gpt-3.5-turbo

references to different levels or floors in buildings and their attributes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cosponsors

-0.79

lez

-0.76

groups

-0.71

christ

-0.70

acci

-0.70

swick

-0.67

è¦ļéĨĴ

-0.65

adden

-0.65

wik

-0.64

thal

-0.64

POSITIVE LOGITS

 foundation

0.68

edly

0.67

endment

0.66

 è£ıè

0.65

Interstitial

0.63

 gravity

0.63

 ground

0.62

 basis

0.61

ioxide

0.61

 bases

0.60

Activations Density 0.145%

phrases related to physical location and architecture, particularly with a focus on features like floors and levels

references to different levels or floors in buildings and their attributes

No Comments

No Known Activations