INDEX

Explanations

phrases related to the act of observing or searching, often emphasizing direction or focus

oai_token-act-pair · gpt-3.5-turbo

phrases related to visual perception or looking at something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

TOP

-0.70

Skill

-0.64

Requ

-0.58

cia

-0.58

 oxid

-0.56

States

-0.56

Wil

-0.55

 informal

-0.54

wealth

-0.54

 itiner

-0.54

POSITIVE LOGITS

WARD

0.85

wards

0.82

imilar

0.77

 favorably

0.74

oward

0.72

 Compass

0.71

zag

0.69

 Borders

0.69

ridor

0.67

 noses

0.64

Activations Density 0.131%

phrases related to the act of observing or searching, often emphasizing direction or focus

phrases related to visual perception or looking at something

No Comments

No Known Activations