INDEX

Explanations

terms related to physical fluids, such as liquids and bodily fluids

oai_token-act-pair · gpt-3.5-turbo

references to fluid substances or their properties

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

################

-0.77

BOOK

-0.77

ãģ®å

-0.76

||||

-0.73

ODUCT

-0.70

ä½ľ

-0.68

ãģ«

-0.67

ulhu

-0.66

ãģ§

-0.66

âĺ

-0.65

POSITIVE LOGITS

 fluid

1.05

pedia

1.00

ious

0.98

iltration

0.95

 fluids

0.94

ity

0.93

 resusc

0.90

flush

0.88

ly

0.88

culus

0.87

Activations Density 0.018%

terms related to physical fluids, such as liquids and bodily fluids

references to fluid substances or their properties

No Comments

No Known Activations