INDEX

Explanations

instances of the word "free"

oai_token-act-pair · gpt-3.5-turbo

expressions related to freedom

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

 Everywhere

-0.78

ç¥ŀ

-0.76

 Authority

-0.69

 Ancients

-0.68

Io

-0.66

 Hale

-0.66

 Conrad

-0.66

BuyableInstoreAndOnline

-0.66

 Shogun

-0.64

 Takeru

-0.63

POSITIVE LOGITS

estyle

1.01

ety

0.99

eware

0.97

ighter

0.97

eways

0.96

eport

0.96

bies

0.95

natureconservancy

0.95

ck

0.95

tted

0.94

Activations Density 0.010%

instances of the word "free"

expressions related to freedom

No Comments

No Known Activations