INDEX

Explanations

words related to the concept of freedom

oai_token-act-pair · gpt-3.5-turbo

instances of the word "free" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Ancients

-0.73

 Everywhere

-0.73

 Takeru

-0.71

 Conrad

-0.70

BuyableInstoreAndOnline

-0.70

 Authority

-0.70

Io

-0.69

 Prohibition

-0.67

ç¥ŀ

-0.66

 Archdemon

-0.65

POSITIVE LOGITS

ety

1.01

bies

0.97

eways

0.95

ck

0.94

ighter

0.94

estyle

0.94

natureconservancy

0.94

eport

0.93

eware

0.93

fre

0.89

Activations Density 0.007%

words related to the concept of freedom

instances of the word "free" in various contexts

No Comments

No Known Activations