INDEX

Explanations

phrases related to coding and programming

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly commas

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

¬¼

-0.67

uscript

-0.67

irie

-0.64

ocl

-0.62

 advisory

-0.61

ahu

-0.61

 investig

-0.60

—

-0.60

Å«

-0.60

 accuser

-0.59

POSITIVE LOGITS

 haha

1.26

 namely

1.22

etc

1.16

ie

1.09

aka

1.05

 albeit

1.05

 whereas

1.01

 whilst

1.00

 although

1.00

 preferably

1.00

Activations Density 0.995%

phrases related to coding and programming

punctuation marks, particularly commas

No Comments

No Known Activations