INDEX

Explanations

phrases related to the external appearance or location of objects

oai_token-act-pair · gpt-3.5-turbo

references to the concepts of "inside" and "outside."

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

iji

-1.04

enegger

-0.81

arcity

-0.78

thumbnails

-0.75

ute

-0.75

lda

-0.74

illed

-0.73

Corp

-0.70

wo

-0.70

 Rampage

-0.70

POSITIVE LOGITS

 workings

0.81

 underside

0.75

most

0.74

 track

0.71

 panel

0.70

 wing

0.70

 diameter

0.70

 observer

0.68

 casing

0.67

 flap

0.67

Activations Density 0.053%

phrases related to the external appearance or location of objects

references to the concepts of "inside" and "outside."

No Comments

No Known Activations