INDEX

Explanations

terms that pertain to words and their arrangement in a document

oai_token-act-pair · gpt-3.5-turbo

terminology and phrases related to the concept of "wording" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

elsen

-0.81

ideo

-0.76

earned

-0.73

Deg

-0.70

ald

-0.69

rium

-0.69

ersen

-0.69

 Stanton

-0.68

å£«

-0.67

Drive

-0.66

POSITIVE LOGITS

 wording

1.50

 guiActiveUn

1.00

terday

0.89

 typo

0.83

phr

0.78

 spelling

0.77

 incorrect

0.75

 instructions

0.74

wip

0.73

 formulation

0.72

Activations Density 0.009%

terms that pertain to words and their arrangement in a document

terminology and phrases related to the concept of "wording" and its variations

No Comments

No Known Activations