INDEX

Explanations

words related to the element "argon."

oai_token-act-pair · gpt-3.5-turbo

terms related to arguments in a debate or discussion context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

emetery

-0.94

TPS

-0.76

idad

-0.74

CLASSIFIED

-0.74

eor

-0.74

arthy

-0.68

isSpecialOrderable

-0.67

grades

-0.66

itizens

-0.65

dates

-0.64

POSITIVE LOGITS

uments

1.39

ument

1.21

uing

0.97

acle

0.86

Arg

0.86

ansas

0.84

ued

0.83

uably

0.82

ues

0.79

ĳ

0.77

Activations Density 0.008%

words related to the element "argon."

terms related to arguments in a debate or discussion context

No Comments

No Known Activations