INDEX

Explanations

instances of the word 'cynabal'

oai_token-act-pair · gpt-3.5-turbo

references to a specific brand or product related to technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Tennessee

-0.73

NS

-0.69

 Jennings

-0.68

 Sony

-0.66

 Shot

-0.65

 plaintiff

-0.61

 Pres

-0.61

 America

-0.60

 Schmidt

-0.59

 reinstated

-0.58

POSITIVE LOGITS

abal

5.30

 cabal

1.27

kell

1.08

ambo

1.05

ibal

1.03

ulhu

0.99

alid

0.99

 Haskell

0.99

ursed

0.98

alam

0.94

Activations Density 0.032%

instances of the word 'cynabal'

references to a specific brand or product related to technology

No Comments

No Known Activations