INDEX

Explanations

words related to classification or categories

oai_token-act-pair · gpt-3.5-turbo

instances of the word "class" and its variations in different contexts

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

hiba

-0.68

aukee

-0.64

OPLE

-0.62

obin

-0.62

foreseen

-0.61

 stump

-0.61

vernment

-0.61

orthy

-0.61

BAT

-0.58

vind

-0.57

POSITIVE LOGITS

ifications

1.40

ifier

1.31

ifiers

1.29

ifying

1.26

ifies

1.21

ifiable

1.16

ified

1.12

ification

1.06

ically

1.06

room

1.05

Activations Density 0.042%

words related to classification or categories

instances of the word "class" and its variations in different contexts

No Comments

No Known Activations