INDEX

Explanations

proper nouns and names of people or places

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to characters or entities involved in dramatic or significant events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ibrary

-0.65

ename

-0.61

lict

-0.61

 Albany

-0.61

 Seym

-0.59

 Serie

-0.59

actionDate

-0.59

BuyableInstoreAndOnline

-0.59

 Byzantine

-0.56

utory

-0.55

POSITIVE LOGITS

 accordingly

1.52

 thereafter

1.20

 alike

1.20

 consequently

1.17

 therein

1.17

 thereof

1.15

 knows

0.94

 subsequently

0.94

 thereto

0.94

 became

0.93

Activations Density 0.502%

proper nouns and names of people or places

proper nouns related to characters or entities involved in dramatic or significant events

No Comments

No Known Activations