INDEX

Explanations

text related to equipment, tools, or products

oai_token-act-pair · gpt-3.5-turbo

punctuation marks at the end of sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

pse

-1.01

umably

-0.88

 anyway

-0.83

 presumably

-0.81

 inconsist

-0.80

 corrid

-0.78

 inco

-0.76

 somewhat

-0.76

 satell

-0.73

 attrition

-0.73

POSITIVE LOGITS

 Featuring

1.70

 Whether

1.54

 Designed

1.50

 Includes

1.41

 Explore

1.41

 Learn

1.35

 Each

1.35

 Discover

1.34

 Available

1.33

 Inspired

1.32

Activations Density 0.357%

text related to equipment, tools, or products

punctuation marks at the end of sentences

No Comments

No Known Activations