INDEX

Explanations

parenthetical expressions within a text

oai_token-act-pair · gpt-3.5-turbo

parentheses and contextual information enclosed within them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 tears

-0.74

 Tears

-0.67

 Bees

-0.66

 Keeper

-0.65

 federation

-0.65

obia

-0.64

 Stard

-0.62

Inn

-0.62

 Bris

-0.62

 Lynd

-0.61

POSITIVE LOGITS

albeit

1.37

yet

1.12

sic

1.10

sounding

1.03

non

1.01

but

1.00

meaning

0.91

though

0.91

sometimes

0.89

pun

0.89

Activations Density 0.119%

parenthetical expressions within a text

parentheses and contextual information enclosed within them

No Comments

No Known Activations